Faculty Profiles - YOSHINO Takashi

Published Papers - YOSHINO Takashi

Division display >> ／ All the affair displays1 - 88 of about 88

Baseless-Rumor Alert Bot to Promote Reliability of Information.

Ryota Nishimura, Mai Miyabe, Takashi Yoshino （Part： Last author,　Corresponding author )

J. Inf. Process. 30 2 - 14 2022 [Refereed]

DOI

ユーザの可視化と視覚的表現を用いた現実空間からVR空間への情報伝達手法

石丸敬登, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 66 ( 1 ) 11 - 20 2025.01 [Refereed]

TOWAN：360度カメラを用いた地震対策箇所提示システム

山中永遠, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 66 ( 1 ) 2 - 10 2025.01 [Refereed]

ID-POSデータの属性を活用可能とした標準化PI値の提案

井口拓己, 中村綾乃, 吉野孝, 松山浩士, 貴志祥江, 大西剛（Part： Corresponding author )

情報処理学会論文誌 66 ( 1 ) 66 - 77 2025.01 [Refereed]

生活習慣の改善維持を目的としたチャットボットの提案

加藤美希, 井口拓己, 吉野孝, 高木伴幸, 小池廣昭（Part： Corresponding author )

66 ( 1 ) 78 - 88 2025.01 [Refereed]

Analysis for Proposing Personalized Lifestyle Improvement Using Bayesian Networks

井口拓己, 吉野孝, 高木伴幸, 小池廣昭

情報処理学会論文誌ジャーナル(Web) 65 ( 1 ) 2024

Long-distance Spatial Movement in Virtual Space Using Physical Movements and Movement Expressions

石丸敬登, 吉野孝

情報処理学会論文誌ジャーナル(Web) ( 情報処理学会 ) 64 ( 1 ) 67 - 76 2023.01

現在，VRなど仮想空間を利用した多くのコンテンツが開発されている．その普及にともない，仮想空間において長距離を一瞬で移動するなど実現不可能な現象が利用されているが，このような実現不可能な現象には，新しい適切な表現を行う必要があると考えられる．そこで本研究では，仮想空間における長距離の空間移動表現の検証用のシステムとして「ドアクル」を開発した．ドアクルは，仮想空間において身体的動作による操作方法および仮想空間特有の表現を用いることによって，「遠く離れた場所に移動した感覚」を向上させることを目指す．比較実験の結果，身体的動作による操作方法と仮想空間特有の表現を用いた空間移動表現は，移動した感覚や没入感などのユーザに与える様々な感覚を向上させることを確認できた．
Currently, numerous contents are being developed using virtual space, such as VR. With its widespread use, unrealizable phenomena, such as moving long distances in an instant are being realized in virtual space. However, it is believed that it is necessary to design and create new and appropriate expressions for such phenomena. Therefore, in this study, a system for verifying long-distance spatial movement expression in virtual space, namely, “Doorcle” was developed. Doorcle aims to improve the “feeling of moving to a distant place” using the operation method involving physical movements and expressions peculiar to the virtual space in. As a result of a comparative experiment, it was confirmed that the spatial movement expressions using the operation method and expressions peculiar to virtual space improve the various sensations given to the user, such as the feelings of movement and immersion.

DOI

Feature Analysis of Rumors in which a Large Amount of Correction Information is Transmitted on Twitter

草竹大暉, 平林(宮部) 真衣, 吉野孝

情報処理学会論文誌 ( 情報処理学会 ) 64 ( 1 ) 24 - 32 2023.01

マイクロブログサービスの1つであるTwitterでは，正しい情報だけでなく，流言を含む情報も発信されることがある．流言には社会的混乱を引き起こすような内容のものがあり，流言が広がりにくい仕組みを作る必要がある．そこで本研究では，真偽が不明，または真偽が人々に疑われている情報を流言と定義し，Twitter上で多数の訂正情報が発信される流言の特徴を分析する．分析の結果，Twitter上で多数の訂正情報が発信される流言の特徴として以下の3点を明らかにした．(1)訂正ツイートの多さは，流言ツイートの多さを必ずしも反映しない．(2)流言ツイートと訂正ツイートのバーストのタイミングには，差がほとんどみられず，両者ともに短期的に収束する傾向がある．(3)今回分析した8つの流言については，いずれも流言ツイートの発生は単発的かつ短期収束傾向がある．一方，訂正ツイートの推移に関しては，その対象となる流言ツイートのTwitter上での拡散数により，傾向が変わる可能性がある．
Twitter, a microblogging service, transmits not only correct information, but also sometimes transmits information that contains rumors. Some of these rumors may cause social confusion. Hence, it is necessary that a system is created to prevent the spread of such rumors. In this study, the meaning of “rumor” is defined as information of which truth or falsity is unknown or suspicious. Further, the characteristics of the “rumors” being transmitted extensively on Twitter are analyzed. The results reveal three features of such “rumors” in which a large amount of correction information is transmitted on Twitter: (1) The number of correction tweets does not necessarily reflect the number of rumor tweets. (2) There is almost no difference in the burst timing between the rumor tweet and the correction tweet, and both tend to converge in the short term. (3) In all of the eight rumors analyzed in this study, the occurrence of the rumor tweet tended to be one-shot and converged in a short period of time. On the other hand, regarding the trend of the correction tweet, the trend can change depending on the number of the rumor tweet spread on Twitter.

DOI

Anna-chan: Proposal for a Chatbot to Provide an Impetus for Discussion among Family Members about Disaster Prevention

小西杏奈, 福島拓, 吉野孝

情報処理学会論文誌 ( 情報処理学会 ) 64 ( 1 ) 77 - 85 2023.01

防災対策の一環として，防災に関する家族間の話し合いがある．しかし，内閣府の世論調査から，約4割にものぼる人が話し合いを行っていないことが分かった．そこで我々は，LINE上からの定期的な通知や擬人化により，防災に関する家族間の話し合いのきっかけを提供するチャットボット「あんなちゃん」を開発した．あんなちゃんは防災に関する家族間の会話のきっかけを提供する．話し合いの中に防災関係のキーワードが含まれていた場合には，防災情報の提供を行う．話し合いのきっかけとして，2種類の防災に関するヒント（防災に関する問いかけ，防災に関する4コマ漫画）を提供している．実験の結果，次の知見を得た．(1)手軽に利用できるLINE上のチャットボットを用いることで，防災に関する家族間の話し合いのきっかけを提供できる可能性を示した．(2)適切な防災情報を提供することにより，防災意識を向上させる可能性が高いことを確認できた．また，単に，防災に関する話題だけでは，防災意識の向上にはつながらないことが分かった．
Family discussions on disaster prevention are a part of disaster prevention measures. However, a public opinion survey conducted by the Cabinet Office of Japan revealed that 40% of people in Japan did not hold such discussions. Therefore, a chatbot named “Anna-chan” was developed to provide opportunities for family discussions on disaster prevention through regular notifications and anthropomorphism on LINE. Anna-chan provides an opportunity for family members to talk about disaster prevention. When disaster prevention-related keywords are included in the discussion, Anna-chan provides information regarding disaster prevention. Two types of hints on disaster prevention (questions on disaster prevention and a four-panel cartoon on disaster prevention) are provided as triggers for such discussions. The experimental results were as follows. (1) The chatbot is easy to use and can provide an opportunity for family members to discuss disaster prevention. (2) It was confirmed that providing a four-panel cartoon about disaster prevention has a high potential for raising awareness regarding disaster prevention. The results further showed that simply talking about disaster prevention does not lead to an increase in disaster awareness.

DOI

Evaluation of a Class Support Chatbot to Encourage Students to Ask Questions

鈴木舜也, 吉野孝

ヒューマンインタフェース学会論文誌(CD-ROM) 25 ( 2 ) 2023

Analyzing the Process of Disseminating Rumor-correction Information on Twitter during the COVID-19 Pandemic

平林(宮部) 真衣, 吉野孝, 河添悦昌

情報処理学会論文誌 ( [出版社不明] ) 63 ( 1 ) 29 - 44 2022.01 [Refereed]

非常事態下では流言が拡散しやすく，マイクロブログ上での対策の検討は急務である．本論文では，新型コロナウイルス感染症流行（非常事態）下でのTwitter（マイクロブログ）上の流言の特徴を，約6カ月分の流言訂正データにより分析した．分析の結果，非常事態下におけるマイクロブログ上の流言には特徴が見られ，今後流言対策において考慮すべき特徴として以下の点を明らかにした．（1）期間全体では，収集される流言情報全体のうち非常事態関連の流言が占める割合は少ないが，日によって割合は異なり，多くの割合を占める日もある．また，割合が急増する前には，原因と考えられる実社会上の出来事が存在する場合がある．（2）非常事態関連の流言の内容は11種類の主題に大別され，人間の行動につながりうる内容や，社会的に影響を与えうる内容が含まれた．これらは，個人・社会一般の「経済状況」や「精神的健康状態」に対して悪影響を及ぼす可能性がある．（3）期間中の訂正数の推移を分析した結果，特定期間に集中的に発生した後に収束していくものと，訂正数の突出箇所が期間中に複数出現するものが見られた．（4）マイクロブログ上の流言拡散には，従来の流言流布に関する知見が適用できない可能性がある．
Emergency situations often facilitate rumor mongering; thus, it is imperative to study methods to eliminate this problem. This study analyzed the characteristics of microblogging during the coronavirus pandemic. The analysis based on six months of microblogging rumor correction-related data showed that some characteristics of microblogging in emergency situations should be considered in order to counter the spread of rumors through microblogs in the future. (1) In the entire dataset, the proportion of rumors regarding the emergency compared to total rumors was low. However, this proportion showed considerable daily variation, with some days accounting for a larger proportion. Moreover, real-world events caused by rumors could occur before this proportion increased. (2) Rumors regarding the emergency were classified into 11 types, which contained information that could incline people toward showing some behaviors or make a difference to someone socially. Moreover, they could negatively affect individuals' economic and mental health conditions. (3) The study identified the following types of rumors: (A) rumors that decreased after an initial rapid increase during a short period and (B) rumors that increased during some periods. (4) Knowledge from previous studies on oral communication may not apply to rumor spreading on microblogging systems.

DOI

Agent Simulation System Using ID-POS Data for Customer Flow Line Analysis

中村綾乃, 吉野孝, 松山浩士, 貴志祥江, 大西剛（Part： Corresponding author )

情報処理学会論文誌 ( [出版社不明] ) 63 ( 1 ) 56 - 65 2022.01 [Refereed]

店舗内における客の行動を把握することで，店内のレイアウトの改善や品揃えの改善につながる．客の行動を詳細に把握する方法として，客動線分析という手法がある．しかし，実際に客の軌跡をたどって記録をすることはコストが高い．そこで，日々の客の購買データが自動で蓄積されるID-POSデータに着目し，ID-POSデータのみを用いた客動線分析ができないかと考えた．本研究では，客動線のシミュレーションを行うシステム「POSパワー」を開発した．POSパワーではID-POSデータのみを用いて客の購買行動のシミュレーションを行う．シミュレーションの結果，ID-POSデータだけでは見つけることが困難な，客の購買行動を再現する経路を可視化できる可能性を示した．
Understanding the behavior of customers in a store can aid in improving the store layout and product assortment for better sales. Customer flow analysis can be used to understand customer behavior in detail; however, tracing and recording of the trajectory of each customer can be highly expensive. Therefore, we focused on using ID-POS data, which are daily customer purchase data that are automatically collected, and hypothesized the possibility of analyzing customer flow lines by only using these data. We developed a system called “POS Power” to simulate customer behavior using the ID-POS data. The simulation results showed that our system can visualize a path that reproduces the purchase behavior of customers, which is otherwise difficult to achieve with only ID-POS data.

DOI

Proposal of Spatial Connection Expression Using Point-cloud Information in Real Space

本信敏学, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 ( [出版社不明] ) 63 ( 1 ) 21 - 28 2022.01

ビデオチャットは，複数の地点にいる人々が1つの仮想空間に集まってコミュニケーションをとることを可能にした．しかし，ビデオチャットは対面環境と比べて，対話相手に心理的な距離感を生じさせる問題がある．そこで本研究では，仮想空間内で遠隔地間の実空間の点群情報を表示する遠隔インタラクションシステムを提案する．提案手法は，片方の実空間を共有する表現や1つの仮想空間に集まる表現ではなく，相互の空間をつなぐ表現である．我々は，遠隔地どうしのインタラクションにおいて，人の身体情報以外に，互いの周辺環境の情報も重要だと考えている．そこで，身体映像だけではなく，部屋内の状況共有のために，空間接続表現と空間移動表現を実装し，評価実験を行った．実験の結果，提案手法は同室感や空間連結感が向上し，より対面環境に近づいたインタラクションが可能であることが分かった．また，ユーザの身体映像に加えて，周辺環境の情報が遠隔インタラクションにおいて重要であることを確認した．
Video chat enables people in multiple locations to gather and communicate in a single virtual space. However, compared to face-to-face environments, video chat has the problem of creating a psychological distance between the interactants. Therefore, in this study, we propose a remote interaction system that displays real space point cloud information between remote locations in a virtual space. The proposed method is not a representation that shares one real space or gathers in one virtual space, but a representation that connects mutual spaces. In addition to physical information, we believe that information about each other's surrounding environment is also important in remote interaction. In order to share not only the body image but also the situation in the room, we implemented a spatial connection expression and a spatial movement expression, and conducted an evaluation experiment. From the experimental results, we found that the proposed method improves the sense of room sharing and spatial connectivity, and enables interaction that is closer to a face-to-face environment. In addition to the user's body image, we confirmed that information about the surrounding environment is important for remote interaction.

DOI

Presentation Methods for Spreading Awareness about Groundless Rumors Featured by Webpages

梅本美月, 吉野孝, 平林(宮部)真衣（Part： Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 183 - 192 2021 [Refereed]

Development and Evaluation of Restaurant Search System by “Palatability” Information

吉野孝, 森田真季, 平林(宮部)真衣（Part： Lead author,　Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 160 - 170 2021 [Refereed]

Development of a Geotour Support System to Assist Guide Explanation

西村涼太, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 125 - 135 2021 [Refereed]

RumorFinder: Release and Its Evaluation of Information-truth Confirmation Prompting System

柿本大輔, 平林(宮部)真衣, 荒牧英治, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 193 - 203 2021 [Refereed]

Development of a System for Providing Disaster Prevention Information to International Tourists

志垣沙灯子, 吉野孝, 永井隼人, 佐野楓, RITCHIE Brent W., RITCHIE Brent W. （Part： Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 204 - 213 2021 [Refereed]

Development of Identification Support System Using Dental Information

安田大誠, 吉野孝, 玉川裕夫（Part： Corresponding author )

情報処理学会論文誌ジャーナル(Web) 62 ( 1 ) 171 - 182 2021 [Refereed]

International tourists’ knowledge of natural hazards. Annals of Tourism Research

Annals of Tourism Research 81 2019.02 [Refereed]

Multilingual Parallel Texts Creation Method Using Accurate Texts Created by Monolingual Users and Perforated Texts

福島拓, 吉野孝（Part： Last author )

情報処理学会論文誌 60 ( 1 ) 166 - 173 2019.01 [Refereed]

Parallel text is often used in fields where accurate multilingual communication support is required. It is a multilingual corpus that can perform accurate multilingual conversion. The volume of parallel texts available has been inadequate because they were all created manually. In this paper, we propose and evaluate a multilingual parallel texts creation method using a perforated text whereby words in the texts can be interchanged. This method uses accurate texts created in each language by monolingual users and multilingual pairs of perforated texts. The major contributions of this study are as followings. (1) We proposed and developed a multilingual parallel texts creation method using perforated texts. (2) The proposed method can create accurate parallel texts by using perforated texts and filling words being guaranteed accuracy.

Evaluation of a Cooperative Patient Information System for Home Care Providers

山本理絵, 吉野孝, 西端めぐみ, 中井國雄, 柳本将喜, 入江真行

情報処理学会論文誌 59 ( 5 ) 1351 - 1362 2018.05 [Refereed]

It is important to cooperate and share information among multi-professional healthcare providers involved in home medical care. However, many of the regional medical cooperation systems built in Japan focus on "one-way" information collaboration. Therefore, we explore two research subjects: "sharing of information in both directions" and "simplification of input forms." We developed a patient information sharing system for home healthcare cooperation focusing on communication support. Moreover, we analyzed the usage of the system based on the system logs. The contributions of this study are as follows. (1) By using a separate system specializing in communication support, multi-professional healthcare providers are able to share information both ways for cooperative medical care. (2) In the system, a patient's medical record and home nursing record, and a video of a patient's home environment can be shared online. This study shows that multi-professional healthcare providers can share information with comparative ease using the proposed system.

Proposal of an Integrated Support System for Disaster-preparedness Map Making Through Town-walk Type of Gathering Information

榎田宗丈, 福島拓, 吉野孝, 杉本賢二, 江種伸之（Part： Corresponding author )

情報処理学会論文誌 59 ( 3 ) 992 - 1004 2018.03 [Refereed]

Throughout Japan, disaster-preparedness maps have been made by the method of town-walk. This method improves disaster-preparedness and allows for a greater understanding of the area. The making of disaster-preparedness maps increases the disaster awareness of the participants. Further, the involvement improves participants' ability of self-help and increases cooperation in local communities. Currently, there is a system to support the making of conventional disaster-preparedness maps, but no support system for maps made using the town-walk method. Therefore, we have proposed and developed an integrated support system for the making of disaster-preparedness maps by gathering information from the town-walk. We conducted a comparison experiment between the proposed system and the conventional system (using paper maps). This experiment demonstrated that a consistent support function would be effective in developing disaster-preparedness maps using the town-walk method. We also confirmed that the proposed system influences the improvement of disaster-preparedness awareness, the understanding of the area, and the conventional system.

流言に関する気づきを提供するシステムの構築

柿本大輔, 宮部真衣, 荒牧英治, 吉野孝

ヒューマンインタフェース学会論文誌 20 ( 1 ) 1 - 11 2018.02 [Refereed]

Proposal of Parallel Texts Creation Method Using Multiple Machine-translation by Monolingual on Crowdsourcing Workers

山本里美, 福島拓, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 59 ( 1 ) 76 - 85 2018.01 [Refereed]

Our former study showed that crowdsourcing workers, even they are monolingual speaker, can make correct parallel texts to request tasks. There is a difference in the translation accuracy of the machine translation according to the sentences of the translation target. It is difficult to create bilingual sentences for many sentences. In this paper, we propose a method to use a sentence adapted to machine translation and to use multiple machine translation engines for the conventional method. A sentence adapted to machine translation is a sentence that is almost the same as the original, but the appropriate machine translation is done. We aim to improve the accuracy of machine translation sentences in the sentences of a machine translation with a low accuracy. The contribution of this paper is as follows. We proposed a method to use a sentence adapted to machine translation and to use multiple machine translation engines in the conventional method for the conventional method. We also proposed a combination of evaluation by the person and the evaluation by the computer as a method of evaluation of a sentence adapted to machine translation. We have shown that the proposed method is capable of making the appropriate machine translation sentences in the original 39 of 40 sentences (97%) with of 25 points higher than the conventional method.

Correctness Evaluation Method for Multilingual Parallel Texts Using Ratio of Working Times of Workers via Crowdsourcing

福島拓, 吉野孝（Part： Last author )

情報処理学会論文誌 59 ( 1 ) 69 - 75 2018.01 [Refereed]

Generally, multilingual support systems for applications requiring high accuracy use multilingual texts pairs called "parallel texts." Accuracy evaluation is important for providing parallel texts. However, because there are huge quantities of parallel texts, it is difficult to thoroughly collect accuracy evaluations. In this paper, we propose a correctness evaluation method for parallel text-candidates using crowdsourcing. This method ranks workers via crowdsourcing based on their ratio of work time. This idea aims to preferentially select workers who evaluate accurately. The major contribution of this study is a correctness evaluation method of parallel text candidates, having a higher accuracy than that of existing methods. Furthermore, the proposed method ranks workers based on their ratio of working time.

Extraction Method of Impressions about Tourist Spots from Tweets without Tourist Spot Names

渡邉小百合, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 59 ( 1 ) 43 - 51 2018.01 [Refereed]

New needs for tourist spots may arise because the appearance of new forms of travel in Japan, in which fans visit the locations of dramas and animated programs, and the number of foreign travelers to Japan has increased in recent years. Therefore, tourist spot operators want to know the needs of tourists and any problems with the tourist spot so that they can be solved. However, insufficient tourist information was provided by Twitter. In this study, we propose an extraction method of impressions about tourist spots to apply to tweets that do not contain tourist spot names. The experiments provided the following four results: (1) Tweets containing feature words contain tourist information. (2) Tweets without tourist spot names tweeted before and after tweets containing tourist spot names contain tourist information. (3) Replies to tweets containing tourist spot names contain tourist information. (4) Tweets with images that do not contain tourist spot names contain information regarding the food and entertainment available at tourist spots.

Construction of Information-credibility Verification-behavior Facilitation System for Preventing False Rumors Spreading

柿本大輔, 宮部真衣, 荒牧英治, 吉野孝

ヒューマンインタフェース学会論文誌(CD-ROM) 20 ( 1-4 ) 2018

Construction of Information-credibility Verication-behavior Facilitation System for Preventing False Rumors Spreading

Kakimoto Daisuke, Miyabe Mai, Aramaki Eiji, Yoshino Takashi

The Transactions of Human Interface Society ( Human Interface Society ) 20 ( 1 ) 1 - 12 2018 [Refereed]

As the widespread of microblogs, we are now capable of obtaining and conveying various information. Microblogs can send out information easily and in real-time, on the other hand, they may widely spread uncertain and false rumors. One of the factors that false rumors are spread is the lack of confirmation about the credibility of the information before retweeting. In this study, we have developed a system to make aware of existence of rumor in web browsing. We found that the proposed system can make aware of existence of rumor and does not disturb web browsing. This system can provide the awareness about rumors to users in web browsing, and can prevent spreading uncertain rumors.

DOI

The Expression of 3-D Movement which Can Give a Feeling of Intrusion in Partial Overlay-type Video Chat System

濱上宏樹, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 58 ( 1 ) 189 - 196 2017.01 [Refereed]

近年，Skypeなどの無料でビデオチャットを行えるツールの普及により，容易にビデオチャットを行える環境が整ってきた．そのため，今後は会議などのフォーマルな場面での利用だけでなく，ビデオチャットは，家族や友人とのインフォーマルなコミュニケーションでの利用が増えてくると考えられる．しかし，従来のビデオチャットには，対面環境に比べて対話相手との心理的な距離感を感じてしまうという問題点がある．本研究では，この問題点を改善するため，部分重畳型ビデオチャットシステム「ドアコムZ」の開発を行った．ドアコムZは，現実に存在する枠を介して遠隔地間を仮想的につなぎ，相手の空間とつながっているような表示を行うビデオチャットシステムである．深度情報を用いることで，遠隔空間における三次元的な移動を表現した．遠隔空間内における三次元的な移動の実現により，「遠隔空間において相手の背後に隠れる」「遠隔空間内を指差す」という表現が可能になった．遠隔空間における三次元的な移動の表現の有用性を示すために，侵入感の検証および被侵入感の検証を行った．検証実験より，三次元的な移動の表現は，二次元的な移動の表現に比べ，侵入感を向上させることが分かった．また，両手法ともに被侵入感が得られ，表現による大きな違いはないことが分かった．表現方法に関係なく，自身の空間にある物を指差される映像は，被侵入感を与えることが分かった．In recent years, the spread of tools that free video chat, such as Skype, has facilitate the use of video chat. We think that a video chat can be used in informal communication. However, the conventional video chat has a problem that you feel a sense of distance to a dialogue partner compared with the face-to-face environment. In order to improve the problem, we have developed a partial overlay-type video chat system "DOACOM-Z." DOACOM-Z can connect between remote places virtually through the frame which exists in an actual space. The system can express three-dimensional movement in the remote space using a depth sensor at both places. The system can give both expressions "hiding in the remote space" and "pointing in the remote space." The usefulness of the expression of three-dimensional movement in the remote space, we carried out a verification experiment of a feeling of intrusion and a verification experiment of a feeling of being intruded. From the result of the verification experiments, we found that the expression of three-dimensional movement can improve the feeling of intrusion compared with the expression of the two dimensional movement. In addition, a feeling of intrusion was obtained with both methods. We found that there is no significant differences between expressions. Regardless of the method, the image pointing object in its own space can provide a feeling of being intruded.

Making of Disaster-prevention Maps by Local Residents Using the AkariMap Evacuation Support System

吉野孝, 濵村朱里, 福島拓, 江種伸之（Part： Lead author,　Corresponding author )

情報処理学会論文誌 58 ( 1 ) 215 - 224 2017.01 [Refereed]

多くの市町村がハザードマップや防災マップを発行しているが，保管率や利用率は低い．そのため，電子媒体を利用したハザードマップや防災マップを提供および作成を支援するシステムが多く存在する．また防災マップの作成の過程は，地域の人同士の交流や連携を支援するために利用できるといわれている．そこで，災害発生前から利用可能なオフライン対応型災害時避難支援システム「あかりマップ」を利用し，地域の防災マップを作成する実験を行い，情報通信技術を用いた防災マップ作成における利用可能性や問題点などを考察した．本研究の貢献は以下の3点にまとめられる．(1)地域住民によって情報通信技術を用いて防災マップを作る際に，密集した場所への情報の登録方法や情報の提示方法の工夫が必要である．(2)ゲーミフィケーションを用いて単に情報の登録数を競わせるだけでなく，情報の正確性の確保への貢献も可視化する仕組みが必要である．(3)地域住民による情報通信技術を用いた防災マップの作成のために，情報通信技術に慣れた学生と一緒に防災マップの作成を実施する手法が有効だった．Many municipalities publish hazard and disaster-prevention maps, but the keeping rate and the utilization rate are low. Thus, various electronic media can create and distribute hazard and disaster-prevention maps. The process of making disaster maps is claimed to support exchange and cooperation between people in an area. We have developed an evacuation support system called AkariMap that can be used offline in the aftermath of a disaster. We use AkariMap to make disaster-prevention maps of an area, and we discuss its applicability and the problems of using information and communications technology (ICT). The contributions of this study are as follows. 1) To have residents make a disaster-prevention map by using ICT, we need a device that can register and present information about a congested area. 2) We created a method of visualizing the accuracy of the information, and of encouraging the registration of information via a gamified competition. 3) We showed that the method of making a disaster-prevention map was as effective when employed by residents using ICT as it was when used by a student accustomed to ICT.

日常利用可能なオフライン対応型災害時避難支援システム “あかりマップ” の実環境における利用可能性

濵村朱里, 福島拓, 吉野孝, 江種伸之（Part： Corresponding author )

情報処理学会論文誌 57 ( 1 ) 319 - 330 2016.01 [Refereed]

Proposal of a Pair of Dialogic Parallel Texts Creation Method Using Conversation Sentences on Crowdsourcing

山本里美, 福島拓, 吉野孝（Part： Last author,　Corresponding author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 56 ( 3 ) 1080 - 1089 2015.03 [Refereed]

The opportunities for communication amongst people whose native languages differ are increasing by globalization. However, it is difficult to share exact information among many languages. A parallel text that combines example sentences and their accurate translation are used in a multilingual communication support. There are many required parallel texts. Moreover, it is not easy to collect a sufficient number of parallel texts. In this paper, we propose a pair of dialogic parallel text creation method of requesting correction for a machine translation sentence with low accuracy on crowdsourcing of a monolingual. The proposed method presents the conversation sentences with a machine translation sentence, in order that a worker may make the intention of example sentences easy to guess. The contribution of this paper is to clarify the effect of presentation of the conversation sentence in a pair of dialogic parallel text creation.

Evaluation of the Availability of an Evacuation Support System "AkariMap" before a Disaster for Use During Network Failure

濵村朱里, 福島拓, 吉野孝, 江種伸之（Part： Corresponding author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 56 ( 1 ) 185 - 195 2015.01 [Refereed]

In the aftermath of the Great East Japan Earthquake, many research initiatives were launched in the fields of network and information technology in anticipation of other such major disasters in the future. However, a network cannot be accessed immediately after a disaster. Usually, few people can handle refuge-supporting information spontaneously at travel and business destinations. Furthermore, it is difficult to store refuge-supporting information pertaining to a wide area on a mobile phone. To address these critical issues, we have developed an evacuation support system named AkariMap, that can prompt the user to confirm information to be necessary after a disaster. AkariMap incorporates a notification function that notifies the user of refuge-supporting information at his/her present location by considering movement of the user. After the system notifies the user of refuge-supporting information around his/her location, the user can access AkariMap to obtain the information. Thereafter, the system stores the refuge-supporting information around the user in the mobile phone. The contributions of this study are as follows: (1) We have developed an evacuation support system with a notification function to support continuous use in before disaster. The notification function can prompt a user to confirm refuge-supporting information around the user. (2) Even if people use the notification function in the long term, the system triggers the user to use the system at the place where one is staying. Users can grasp easily refuge-supporting information in about 10 days.

Verification by Presentation of Contribution Information to Users of Motivation to Multilingual Parallel Text Registration Using the Notification Function on Mobile Phone

吉野孝, 西田祥子, 福島拓（Part： Lead author,　Corresponding author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 56 ( 1 ) 118 - 125 2015.01 [Refereed]

Parallel text has been used for accurate multilingual communication and information sharing. The motivation of this research is the lack of parallel text. In recent times, the use of smartphones has increased, and the notification function has been widely employed in smartphones. Therefore, we have developed a registration system called Chocolan, with support for multilingual parallel text. Through experiment 1, we found that the notification function can motivate the users to register example sentences. Moreover, we found the following results from experiment 2: (1) Registration of example sentences is encouraged by each user's contribution information rather than each user's ranking information. (2) The contribution information on the contents of notification information may provide a key to consider a new example sentence.

Paired Dialogue Parallel Text Composition Model for Reliable and Unrestricted Multilingual Communication Support

福島拓, 吉野孝（Part： Last author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 56 ( 1 ) 219 - 227 2015.01 [Refereed]

Recently, worldwide globalization has helped to improve communication among people with different native languages. However, sharing accurate information in many languages is not sufficient. In general, multilingual support systems for applications that require high accuracy use parallel texts, but the context may be incorrect in systems that use existing parallel text systems. Moreover, parallel texts are fixed phrases, i.e., a system can only select a perfectly matching sentence. In this study, we propose a paired dialogue parallel text composition model to resolve the existing problems with multilingual communication support. We also developed this system and conducted an experimental verification of the usefulness of the model. The main contributions of this study are as follows. (1) We propose a model that uses dialogue parallel texts to solve the problems of existing multilingual dialogue support system by using parallel texts. (2) This model collects dialogue parallel texts automatically. We also demonstrate that the model can support the selection of the most appropriate answers. (3) We show that the model can support unrestricted dialogue by connecting similar text with parallel dialogue texts.

Development and Evaluation of a Nutrition Management System for Elderly People with a Dish Registration Function

川島基子, 吉野孝, 紀平為子, 伊井みず穂, 岡本和士, 江上いすず, 藤原奈佳子, 石川豊美, 入江真行（Part： Corresponding author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 56 ( 1 ) 171 - 184 2015.01 [Refereed]

A significant number of elderly people suffer from chronic diseases, such as diabetes and obesity. In general, the elderly are prescribed a medical diet in order to treat such illnesses. However, it is not easy to investigate their eating habits. To the best of our knowledge, the existing methods for monitoring the diet of the elderly are unsuitable. In this paper, we propose a nutrition management system that is easy to use for dietitians as well as the elderly. This system consists of a novel dish registration function that allows users to register various dishes. We evaluated our system by experimenting with 15 subjects with an average age of approximately 70 years. Based on the results of a questionnaire and our system's usage history, we could determine that 13 out of the 15 subjects were able to record their diet daily. Moreover, 11 subjects received reminders from our system to record their diet daily. We propose that the system can perform meal investigation and nutrition management for the elderly. During the experimental period, 314 out of 323 dish data were corrected when the elderly subjects entered new dishes in the system. The dietitians could view this data in the system. We show that our proposed system can provide useful feedback to elderly users.

Proposal of Cultural Difference Detection Method Using Japanese and Chinese Wikipedia

諏訪智大, 宮部真衣, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 55 ( 1 ) 257 - 266 2014.01 [Refereed]

多言語間コミュニケーションにおいて，同一の単語を用いて会話をしている場合でも，相手の文化について十分に理解していないために，誤解が生じる可能性がある．現在，文化差の有無の判断は，人が行う必要があるが，その判断には相手の文化に関する十分な知識が必要となるため，容易ではない．そのため，文化差が存在することを自動的に検出する仕組みが求められている．そこで本論文では，多言語知識のデータベースであるWikipediaを利用した文化差の検出手法を提案する．検討用データセットを分析した結果，文化差のある語句には，Wikipedia記事の本文やカテゴリに特徴が存在することが分かった．そこで，これらの特徴を考慮した手法を検討した．実験の結果，提案手法は，検討用データセットにおけるすべての文化差に関して，最も良い精度で検出することができた．また，「世界的な観点から説明されていない」「日本語版Wikipediaのみで日本について言及されている」「中国語版Wikipediaにおいて中国について偏った表記がされていない」「各言語版Wikipedia内に各国に対する言及表現が存在しない」の特徴を含む記事が，文化差判定において重要であることが分かった．There is a possibility that the misunderstanding is caused in multilingual communications, because people cannot understand enough other culture even when talking by using the same word. People should judge the presence of a cultural difference in today's situation. However, it is difficult to judge it because enough knowledge of other culture is necessary. We proposed a cultural difference detection method using Wikipedia which is a database of multilingual knowledge. From the analysis of data set for examination, We found the feature in the text and category, and others of the articles on Wikipedia. Therefore, We proposed method using these features. From the result of the experiment using data set for examination, we presented that the proposed method can detect correct differences about all kind of cultural differences. We found that the following features of an article are important for detecting cultural difference: (1) An article is not explained from a global viewpoint. (2) An article is mentioned about Japan by Japanese version Wikipedia. (3) An article of the Chinese version Wikipedia is not mentioned which inclined toward China. (4) An article in each language version Wikipedia has not mentioned each country.

Translation Repair Method for Improving Accuracy of Translated Sentences.

Taku Fukushima, Takashi Yoshino 0001

IEICE Trans. Inf. Syst. 97-D ( 6 ) 1528 - 1534 2014 [Refereed]

DOI

Docoitter: A Presence Display System Capable of Predicting Future In-the-room Information

田中優斗, 福島拓, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 54 ( 9 ) 2265 - 2275 2013.09 [Refereed]

現在，様々な手法を用いて在室管理が行われている．在室管理は「現在，誰がどこにいるか」を提示する．これにより，コミュニケーションの円滑化や協調作業を支援できる．しかし，提示する情報は，現在の在室の有無や行き先である．そのため，訪問者は目的の人物が不在の場合，次回の都合の良い訪問日時を把握することが困難である．そこで，我々は，現在の在室情報だけでなく，在室履歴と個人のスケジュールから未来の在室情報を予報する在室管理システム「Docoitter」を開発した．また，大学の研究室での実験から，従来から使用している紙の在室表との比較や，未来の在室情報を提示することによる効果の検証をそれぞれ行った．本研究の貢献は以下の4点にまとめられる．(1)未来の在室情報を予報する在室管理システムの提案を行い，実現した．(2)未来の在室情報の精度向上には，持ち込み計算機を利用する人や一時退席をする人を検出する必要があることを示した．(3)未来の在室情報の提示により，訪問者は研究室メンバの在室状況と訪問日時の手がかりとなる情報を得る可能性を示した．(4)未来の在室情報を提示するシステムは，至急のとき以外で利用される可能性を示した．Recently, a number of presence display systems have been fabricated by various techniques. A presence display system indicates the location of a person. Thus, such a system can facilitate communication and provide support for cooperative tasks. However, this system provides the presence and destination information of persons present. Therefore, if a person is absent, it is difficult to determine the date and time of that person's next visit. In this study, we have developed a system called Docoitter that can predict future in-the-room information about a person on the basis of that person's activity history and personal calendar. We compared the precision of our system with that of a paper-based destination bulletin board; moreover we conducted experiments in which we presented future in-the-room information at the laboratory of a university. The contributions of this study are as follows: (1) we proposed and developed a presence display system capable of predicting future in-the-room information; (2) we showed that to improve the accuracy of in-the-room information, it was necessary to detect persons using a carry-in personal computing device such as notebooks and those leaving momentarily; (3) the proposed system can provide hints regarding a person's in-the-room information, including the visit date and time, so that future in-the-room information on that person can be predicted; and (4) the system which predicts the future in-the-room information showed the possibility of being used in a case except emergency.

Effect of Movement in Three Dimensions and Existence of Frame in Overlay-type Video Chat System

吉野孝, 藤田真吾（Part： Lead author )

情報処理学会論文誌 54 ( 1 ) 249 - 255 2013.01 [Refereed]

我々は，遠隔地対話者の存在感を向上させるシステムとして"ドアコム"を開発した．ドアコムは，ユーザの一方（ドア操作側）がドア型インタフェースを用い，相手の空間（ドア無し側）に現れるような表示をする，重畳表示型のビデオチャットシステムである．これまでの実験から，ユーザの存在感の向上と映像の立体感に関するコメントが得られていた．そこで，本論文では，重畳表示型ビデオチャットシステムであるドアコムのどのような特徴が，存在感の向上と映像の立体感に寄与しているかを検証した．枠の3次元的な動きと枠の存在が，存在感の向上と映像の立体感に寄与していると仮説を立て，2種類の比較用システムを用いて実験を行った．実験の結果，枠の3次元的な動きにより，ドア無し側ユーザに対して，ドア操作側ユーザの存在感が向上することを示した．さらに，枠の存在により，ドア無し側ユーザに対して，ドア操作側ユーザの存在感と映像の立体感が向上することを確認した．We have developed an overlay-type video chat system called "DOACOM" that enhances the presence of a talker who is at a distance. DOACOM has a door-type interface. When a user opens the door in front of a Web camera, he/she (hereafter referred to as the user on the door-operation side) appears in the other users' (on the door-less side) room. From the results of previous experiments, we obtain comments that the users felt the improvement of presence and spatial effects. In this study, we investigated the features of DOACOM that influence the presence of a person and spatial effects in a video chat session. We hypothesized that three-dimensional movement and the existence of a frame enhance presence and spatial effects. To verify these hypotheses, we developed two systems and carried out experiments. We found that three-dimensional movement in a frame enhances the presence of a user (on the door-operation side) who is at a distance and that the existence of a frame enhances the presence and spatial effects perceived by the other users (on the door-less side).

Proposal and Evaluation of an Inputting Method for Multilingual Interview Sheet Using Parallel-text and Machine Translation

福島拓, 吉野孝, 重野亜久里（Part： Corresponding author )

情報処理学会論文誌 ( 情報処理学会 ) 54 ( 1 ) 256 - 265 2013.01 [Refereed]

現在，在日外国人数は年々増加しており，多言語によるコミュニケーションの機会は増加している．医療の分野では医療機関を訪れる外国人患者とのコミュニケーションのために多言語問診票が使用されている．しかし，多言語対応の紙の問診票は種類が少ないため各医療機関の要求を満たすことができていない．また，日本人医療従事者が外国人患者の母語で書かれた紙の問診票を理解することは困難である．そこで我々は，用例対訳や機械翻訳を利用して診察に必要な基本情報である症状の伝達を支援する，多言語問診票作成システムの開発を行い，問診票入力機能についての評価を行った．本研究の貢献は次の2つである．(1)日本人医療従事者と外国人患者との間のコミュニケーションを支援する，多言語問診票作成システムの提案を行い，実現した．(2)用例対訳と機械翻訳を併用することで，病名や症状を含む文の正確性と，状況説明などの付与情報を含む文の網羅性を確保した多言語問診票の記入の可能性を示した．The number of foreign residents and foreign visitors in Japan has been increasing every year. The opportunities for communication amongst people whose native languages differ are increasing. In healthcare facilities, a paper-based multilingual interview sheet is used to facilitate communication between medical workers and foreign patients. However, this interview sheet has been found to be inadequate for such purposes. Moreover, Japanese medical workers find it difficult to understand the different languages written on a paper-based interview sheet. To resolve this problem, we have developed a multilingual interview-sheet composition system that uses parallel texts and machine translation. This system can convey essential patient information to a medical worker during consultation. Moreover, we have evaluated an inputting method for multilingual interview sheet. The contributions of this study are as follows: (1) We have proposed a multilingual interview-sheet composition system that can be used for communication between medical workers and foreign patients. We have developed this system using both parallel texts and machine translation. (2) This system uses both a parallel corpus and machine translation. As a result, we showed that a patient can write a multilingual interview sheet which has both the accuracy of sentences including disease names and symptoms, and the completeness of sentences including complementary information.

Development and evaluation of an emotional chat system using sense of touch

Hajime Yoshida, Takaya Yuizono, Takashi Yoshino, Jun Munemori

International Journal of Knowledge-Based and Intelligent Engineering Systems 17 ( 3 ) 235 - 242 2013 [Refereed]

A newly developed chat system that uses the sense of touch (via pressure sensors) to communicate a user's feelings is proposed. According to the strength of a user's grasp on a mouse, face marks are entered into a chat window. This system was applied in an electronic conferencing system called a remote seminar support system. Our experiments showed that users found the system to be more interesting than a traditional chat system. © 2013-IOS Press and the authors. All rights reserved.

DOI

Development and evaluation of photo-sharing system using an anthropomorphic photo frame for communication support

Takashi Yoshino, Tomoya Matsuo

Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers 67 ( 2 ) J64 - J73 2013 [Refereed]

Many photo-sharing websites do not actively promote communication among their users. We believe that a website that promotes viewing and commenting on shared photographs should better support communication and relationships between people who do not know each other. Therefore, we have developed a photo-sharing system, named GAZO GAZO KUN. This system has an anthropomorphic photo function (a photo agent), which actively supports communication among users. Our experiments compare GAZO GAZO KUN to a current photo-sharing website in Japan, which is similar to Flickr. We found that the effect of promoting viewing and commenting on photographs in GAZO GAZO KUN was higher than that of the photo-sharing website.

DOI

A Multilingual Parallel-text Sharing System for Accurate Information Sharing

福島拓, 吉野孝, 重野亜久里（Part： Corresponding author )

情報処理学会論文誌コンシューマ・デバイス＆システム（CDS） ( 情報処理学会 ) 2 ( 3 ) 23 - 33 2012.12 [Refereed]

現在，グローバル化による多言語間コミュニケーションの機会が増加している．しかし，多言語間での正確な情報共有は十分に行われていない．この問題は，正確性が求められる医療分野や災害時において顕著に現れ，解決が求められている．このため，正確な情報共有を可能にする一技術である用例対訳を用いた支援が行われており，用例対訳の作成も多く行われている．しかし，従来の用例対訳作成においては， (1) 新たな用例対訳の追加が難しい， (2) 翻訳者 1 人あたりの負担が大きい， (3) 用例対訳の利用現場で求められている用例を収集することが難しい，という問題が存在していた．そこで本論文では，用例対訳の作成の基盤となる場を用例対訳作成環境に提供し，円滑に正確な用例対訳の収集を行うことを目的とした，多言語用例対訳共有システムを提案し，実装を行った．また，実際のシステム構築後に顕在化した問題点とその解決策について述べる．Recently, globalization has helped in increasing communication among people with different native languages. However, accuracy in multilingual information sharing remains a conspicuous problem in fields such as medicine and disaster. Parallel-text has begun to be employed as a solution to this problem. Although several parallel-text sharing projects have been done, these projects face the following problems: (1) It is difficult to generate a new parallel-text. (2) The task of translating many texts places a heavy burden on translators. (3) It is difficult to collect example sentences needed in the using field. Therefore, in this study, we proposed and implemented a new multilingual parallel-text sharing system to improve accuracy. This system provides a base field for producing parallel texts to parallel-text creating groups. Moreover, we identify and solve problems related to the operation of the system.

Integrated Evaluation Using Multiple Translation Systems to Detect Mismatches between Back-translated and Target-translated Sentences

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌 ( 情報処理学会 ) 53 ( 8 ) 2036 - 2043 2012.08 [Refereed]

機械翻訳を介したコミュニケーションでは，翻訳精度が低い場合，十分な相互理解ができない可能性が高い．現在，母語のみを用いて自分の発言がどのように伝わっているのかを把握するための手法として，折り返し翻訳が用いられている．対象言語翻訳文と折り返し翻訳文の精度の同等性に関する検証の結果，対象言語翻訳文が不正確であるにもかかわらず，折り返し翻訳文が正確であるという状況（精度不一致）が発生する場合があることが明らかになっている．このような精度不一致が発生した場合，ユーザの確認する折り返し翻訳文には問題がないため，対象言語翻訳文が低精度であることに気づくことができず，大きな問題となる．そこで本研究では，複数翻訳機を利用した精度不一致の検出手法について検討を行う．検証の結果，提案手法とあわせて対象言語翻訳文中に原言語表現が残っているかどうかを検証する処理を行うことにより，約71%の精度不一致を検出できることを示した．In communication using machine translations, inaccurate translations can lead to misunderstandings. Therefore, it is important to check the accuracy of translations. Back translation is used to verify the accuracy of a sentence translated to a native language. However, a mismatch of accuracy that a translated sentence is inaccurate but its back-translated sentence is accurate sometimes occurs. In this case, people do not understand that a translated sentence is inaccurate because its back-translated sentence is understandable. We found that this mismatch can lead to serious problems in communication. Therefore, we proposed a method for detecting the mismatch in order to prevent such problems. The method obtains multiple back-translated sentences from different translation systems, and judges the accuracy of the translated sentence in a comprehensive manner. We found that the method can detect approximately 71% of the mismatches if combined with prior processing which checks the presence of letters of a source language in the target-translated sentence.

Meta-node Composition Method on Multilingual Parallel-text Graph Having Many-to-many Relationship

福島拓, 吉野孝（Part： Last author )

情報処理学会論文誌データベース（TOD） ( 情報処理学会 ) 5 ( 2 ) 1 - 10 2012.06 [Refereed]

世界的なグローバル化を背景に，我々は多言語間コミュニケーション支援を目的とした多言語用例対訳共有システムの開発を行っている．共有対象の用例対訳は，各言語間で1対1に対応する必要があるが，用例対訳には各言語間で1対1に対応しない言葉の組合せが存在している．このような多言語間の言葉の多様性への対応が求められているが，単純な用例間の意味のつながり情報のみでは対応することができていなかった．そこで，本論文では，1対多，多対多の関係にある用例対訳グラフを提供可能な用例対訳とするために，メタノード作成手法を提案する．また，メタノード作成手法適用により顕在化したリンク不足の問題を解決するために，新たな用例間リンクを発見する方法についても提案する．Recently, there is increasingly globalized world. We developed a multilingual parallel-text sharing system for multilingual communication. A parallel-text requires one-on-one combination among each language. However, parallel texts often have example sentences of many-to-many combination among each language. A multiplicity of expression causes this problem. It is difficult to solve this problem only information of association between example sentences. Therefore, we proposed a meta-node composition method for parallel-text graph having many-to-many combination. Moreover, we proposed a new parallel-text link discovery method to solve latent problems.

Influence of Objective Accuracy Indication in Users' Judgment of Translation Accuracy

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌 ( 情報処理学会 ) 53 ( 1 ) 39 - 48 2012.01 [Refereed]

機械翻訳を利用した多言語間コミュニケーションにおいて不正確な翻訳文を用いると，意思疎通が困難となる．しかし，ユーザは翻訳精度を正しく判断できない場合があるため，翻訳精度に関する気付きを与える必要がある．本研究では，他者やシステムによって判定された精度を提示した場合，ユーザ自身の翻訳精度判定にどのような影響があるかを検証する．本研究の貢献は次の点にまとめられる．(1)誤った精度を既判定精度として提示した場合でも，既判定精度の影響を受ける場合があることを示した．また，正しい精度（本来の精度）を提示した場合，提示した精度との一致率が最も高くなることを示した．(2)本来の精度と隣接した評価値を既判定精度として提示した場合，本来よりも高い隣接評価値との一致率の方が，本来よりも低い隣接評価値との一致率よりも高い傾向があることを示した．In communication using machine translation, inaccurate translations impede mutual understanding between communicating individuals. However, people often make inaccurate judgment of translation accuracy. Therefore, it is necessary to consider a method for preventing them from judging accuracy inaccurately. In this study, we verify the influence of objective accuracy indication in their judgment of translation accuracy. The contribution of this study is as follows: (1) Even if an inaccurate indication was shown, the indication influences their judgment. When an accurate indication was shown, the indication influences subjects' judgment strongly. (2) When a higher adjacent evaluation of accurate evaluation was provided to subjects, the evaluation was more influential on them than a lower adjacent evaluation of accurate evaluation.

Development and Evaluation of the Sustainable Motivation Support System "Example-sentence Forest" for the Evaluation of Example Sentences

狩野翔, 福島拓, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 ( 情報処理学会 ) 53 ( 1 ) 138 - 148 2012.01 [Refereed]

現在，モチベーション維持に関する研究が行われている．しかし，「日常的に行わない」作業を対象とした支援は十分に考慮されていない．「日常的に行わない」作業では，「日常的に行う」作業に対して存在する「やらなければならない」という気持ちが支援対象者の中に少なく，モチベーション維持を支援することは難しい．そこで本論文では，非日常的な作業として「医療分野向け用例の評価」を対象とし，そのモチベーション維持支援を行った．医療分野向けの用例では，医療現場へ提供するために正確性の評価が必要である．しかし，用例数が多く作業のゴールが見えない，評価作業が単調で飽きるといった問題が存在する．そのため，「楽しさ」や「達成感」の要素を用いた用例評価のモチベーション維持支援システム「用例の森」を開発し，評価を行った．本論文の貢献は次の4点にまとめられる．（1）非日常的な作業に対するモチベーション維持支援システム「用例の森」の提案を行い，実現した．「用例の森」は，非日常的な作業である用例の評価活動において，モチベーション維持支援の可能性があることを示した．（2）用例を木に，用例の評価状況を木の成長に見立てることにより，ユーザに「楽しさ」や「達成感」を与えることができ，「評価状況の把握」に役立つことが分かった．また，用例群をいくつかのグループに分け，小さな目標としてユーザに提示することにより，達成感を与えることの補助ができることが分かった．（3）ユーザは自分の登録した用例が評価されると，他のユーザが登録した用例を評価したいと思う傾向があることを明らかにした．（4）ユーザは手軽に達成感を得るために，数の少ない用例群を優先して評価する傾向があることを明らかにした．Recently, scholars have been studied supporting sustainable motivation. However, these studies do not support for "non-daily works." In the context of "non-daily works", it is difficult to apply the sustainable motivation support system because people do not have think that "must do." In our study, we support users' motivation for "Evaluating example sentences in the medical field." In the medical field, example sentences need to evaluate the accuracy of sentences. However, problems related to the evaluation of example sentences have existed; for instance, there is no anticipated end to the evaluation work because there are too many sentences, the work is tedious, and so on. Therefore, we have developed and evaluated a sustainable motivation support system, "Example-sentence Forest" that is used for the evaluation of example sentences employs factors like "fun" and "accomplishment." The contributions of this paper are the following results: (1) We proposed a sustainable motivation support system, this is, "Example-sentence Forest" for non-daily works. The system has a possibility of fostering motivation in users for evaluating works that are non-daily works. (2) It is useful for experiencing a sense of fun and accomplishment and assessing the evaluation that use example sentences resemble to "Trees", and use evaluated status resemble to growth of the Tree. We divided the example-sentences groups into some to present them to users as a small target. We found that a small target can give the sense of accomplishment. (3) We revealed that the user tend to evaluate sentences that drew up by other user when my sentences are evaluated. (4) We revealed that the user tend to evaluate sentence groups that have few sentences.

Development and Evaluation of Face-to-face Intercultural Communication Support System Using Related Information of Nouns in Conversation

岡本健吾, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 ( 情報処理学会 ) 52 ( 3 ) 1213 - 1223 2011.03 [Refereed]

近年，在日外国人が増加しており，外国人と対面でコミュニケーションを行う機会が増加している．しかし，異文化間コミュニケーションにおいては，それぞれの人間が持つ文化的な背景が異なるため，相互理解が困難である．そこで本研究では，文化的な背景がもたらす知識の違いを補うために，会話中の名詞の関連情報を用いた対面型異文化間コミュニケーション支援システムiGengoを開発した．対面環境における異文化間コミュニケーションにおいて，iGengoの評価実験を行い，次の知見を得た．(1)会話中に発言された名詞に関する画像，母語の情報，説明の文章，関連名詞，関連画像をユーザに提示することは対話を効果的に支援する可能性がある．(2)発言された名詞に関連している名詞を表示する機能は，話題に関する情報をユーザに与え，会話の話題を広げられる可能性がある．(3)発言された名詞の画像を複数同時に表示する機能は，多方面，多角度から話題を理解することを支援できる．(4)タッチパネルディスプレイを用いたクリック操作インタフェースと音声入力は会話をしながら手軽に操作を行える．Foreign residents of Japan have increased in these days; the Japanese come to have opportunities for communicating with foreigners in face-to-face environment. However, it is difficult to mutual understanding in intercultural communication. Because the cultural background that each people has is different. In our study, we have developed a face-to-face intercultural communication support system iGengo which visualizes nouns in conversation. We performed an evaluation experiment using iGengo, and obtained the following findings in a face-to-face intercultural communication. (1) It can be useful for users to show the information, such as picture images, information of native language, sentences of the explanation, related nouns and related picture image of spoken noun, during the conversation. (2) The function of display nouns which are related with the spoken nouns will give the information about the topic, and it may wide the topic of the conversation. (3) The function of display multiple images of spoken nouns at the same time can support users to understand a topic from many aspects and many angles. (4) A click operation interface and a voice input using a touch panel display can support users during conversation.

Casual Scheduling Management and Shared System Using Avatar

吉野孝, 山野孝幸（Part： Lead author )

情報処理学会論文誌 ( 情報処理学会 ) 52 ( 3 ) 1234 - 1244 2011.03 [Refereed]

既存のスケジュール管理・共有システムはモチベーションの維持が困難であり，企業内などの特定の環境でしか十分に活用されてこなかった．そこで，モチベーションの維持を目的とし，アバタを用いたスケジュール管理・共有システム「キャラっとスケジュール」を開発した．本システムではスケジュールの入力状況に応じて，アバタを着飾るアイテムが得られる．本システムをmixi上で提供し，評価実験を行った．実験の結果，スケジュール管理・共有システムにおいてアバタを利用することは，ユーザのモチベーション維持のための1つの手段として効果があった．特に，アバタのアイテム獲得に意欲のあるユーザは，そうでないユーザと比べて，スケジュール入力数に大きな差があることが分かった．Conventional scheduling management and shared systems have been used only in some organizations. This is because a user cannot keep his/her motivation to use such a system. Therefore, we have developed a casual scheduling management and shared system using avatar. The dress-up and accessories for each avatar increase depending on the number of items in a schedule. This system can be performed on mixi that is one of famous SNS sites in Japan. From the result of the experiment, we found that our system can keep a user's motivation. Especially, the users who are interested in the items acquisition input their schedule more than the users who are not interested in those.

Effect of All-for-one Type Support for Multilingual Conference Support System

宮部真衣, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 52 ( 1 ) 90 - 96 2011.01 [Refereed]

日本国内の大学などで行われる講義や会議において，外国人留学生の内容理解には限界がある．外国人の内容理解を支援するために，会議に参加している複数の支援者が少しずつ助力することによって支援を行う，All for one型の多言語対面会議支援システムが提案されている．All for one型支援では，本来1名の支援者のみにかかる作業負荷を軽減できる可能性がある．しかし，これまでに作業を分担して支援を行うAll for one型支援における，支援者側の効果についての検証は行われていない．そこで，本論文では，発表要約実験を行い，単一ユーザによる支援と4名の支援者によるAll for one型の支援との比較を行った．実験の結果，以下の知見を得た．(1) 4名の支援者によるAll for one型支援においては，要約の平均総文字数が単一ユーザによる支援の約2倍となっていた．また，All for one型支援におけるスライドカバー率は単一ユーザによる支援よりも有意に高く，All for one型支援は，単一ユーザによる支援よりも多くの情報を入力できていた．(2) All for one型支援における支援者個人の操作数は単一ユーザの操作数よりも有意に少なく，4名の支援者により作業を分担することにより，作業量を軽減できていた．(3) All for one型支援により作業負担は軽減できたものの，支援者の内容理解度に悪影響を及ぼす可能性がある．There is a limitation in the content understanding at a lecture and a conference for foreign students in Japan. All-for-one type multilingual conference support system has been proposed to support content-understandings of foreigners. All-for-one type means that Japanese participants support content-understandings of foreigners at a lecture or a conference in Japan. However, the effect of all-for-one type support has not been verified. We performed an experiment using the all-for-one type multilingual conference support system. In this experiment, we compared the result of support by one supporter and that by four supporters. The following conclusions can be drawn from the results of the experiments: (1) The number of characters in summarized contents by four supporters was twice as many as that by one supporter. Therefore, all-for-one type support can provide more information than the support by one supporter. (2) The number of operations by each supporter in four supporters performed all-for-one support was less than that of the supporter performed the support by one supporter. Therefore, all-for-one support can reduce the supporters' workload. (3) Although the all-for-one-type support can reduce the workload of supporters, their content understanding may be lower than that of single supporters.

Comparison of Methods Used for Accurate Evaluation of Example Sentences

福島拓, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 ( 情報処理学会 ) 52 ( 1 ) 131 - 139 2011.01 [Refereed]

現在，在日外国人数や訪日外国人数は増加傾向にあり，多言語によるコミュニケーションの機会が増加している．多言語環境支援の一方法として，用例を正確に多言語に翻訳した用例対訳が用いられている．用例対訳は正確な多言語間コミュニケーション支援が可能なため，医療分野などの正確性が求められる分野で多く利用されており，動的な用例対訳収集も行われている．しかし，これまで用例対訳を含めた用例収集の取り組みにおいて用例の正確性評価が行われてこなかった．用例の正確性評価がなされていない用例は，医療などの正確性を求められる分野で使用することはできない．そこで我々は，用例の正確性評価手法の確立を目指して複数の評価手法の比較評価を行った．本論文では，比較実験の結果から次の知見を得た．(1)用例の正確性評価実験の結果，評価軸を提示していない評価手法と提示した評価手法の間に相関関係がみられなかった．用例の正確性評価には，評価軸を明確に提示した評価手法が必要である．(2)用例の評価において，評価者は詳細な評価を行うことを好んだ．このため，2値の評価段階よりも複数の評価段階を選択可能とした評価手法が評価者から支持された．Recently, there has been an increase in the number of foreign nationals residing in Japan as well as the number of foreigners visiting the country. Consequently, there may be increased communication among people speaking different native languages. A parallel text that combines example sentences and their accurate translation is used in a multilingual environment, for example, hospitals where the staff members and patients speak different languages. Some researchers are dynamically collecting example sentences or parallel texts. However, they have not yet evaluated the accuracy of the collected sentences. An unevaluated example sentence cannot be used at needed accurate communication fields. Therefore, we evaluated evaluation methods to evaluate example sentence. We observed the following from the experiments in which evaluation methods were compared. (1) From the result of the experiment, there was no correlative relationship between having evaluation axes and not having evaluation axes. It is necessary to indicate the evaluation axis explicitly when using this method. (2) Evaluators prefer detailed evaluation methods, and hence, they supported those methods in which the example sentences are evaluated in multiple steps.

Effect of All-for-one Type Support for Multilingual Conference Support System

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌論文誌ジャーナル ( 情報処理学会 ) 52 ( 1 ) 90 - 96 2011.01 [Refereed]

Availability of Accuracy Judgment of Translation Repair Result in Real-time Remote Text-based Communication via Machine Translation

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌 ( 情報処理学会 ) 51 ( 3 ) 784 - 795 2010.03 [Refereed]

機械翻訳を介したコミュニケーションにおいて，翻訳リペアは重要な役割を果たす．しかし，翻訳リペアは，ユーザが文章の精度が低いと判断した段階で，初めて行われる作業である．そのためユーザによる精度の不正確な判定により，十分にリペアがされていない状態での修正終了などが発生しており，ユーザの不正確判定を減少させるための仕組みが必要である．不正確判定を減少させる仕組みは，理解可能なメッセージのみのやりとりを実現できる．一方で，この仕組みはユーザの行った判定を否定し，修正するよう促すものであり，特に即時的な対応が求められるリアルタイムコミュニケーションへの適用において，様々な問題が発生する可能性が高い．そのため，不正確判定を減少させるための仕組みの適用による影響を検証する必要がある．不正確判定を減少させるための仕組みとして，精度判定を行った結果，低精度であると判断されたメッセージについては対話相手への送信を拒否し，入力者にメッセージの修正を促すシステムを想定する．システムが実現された場合のチャットコミュニケーションへの影響を検証するために，Wizard of Oz（WOZ）法によるチャット実験を行った．実験の結果，以下の知見を得た．(1) 精度判定に基づいた送信拒否の仕組みを適用しない場合，対話自体を進行させることはできるが，送信されたメッセージの精度が低く，意思疎通が成立しない可能性がある．精度判定に基づいた送信拒否の仕組みを適用する場合，より高精度な対話を行うことができ，意思疎通が成立する可能性が高くなる．また，仕組みを適用しない場合と適用した場合とを比較して，対話の円滑性に大きな差異があるとはいえない．そのため，正確性の求められるコミュニケーションにおいては，低精度なメッセージ送信の防止が適用できる可能性がある．(2) 精度判定の結果が悪いものについて，単に送信を拒否し，修正するよう促すだけでは，ユーザの判断を否定することになり，またどの部分をどのように修正すべきかをユーザが判断できない場合もあるため，ユーザにとって不快度が高かった．そのため，低精度なメッセージ送信の防止を単純にチャットコミュニケーションへ適用することは難しい．In multilingual communication using machine translation, translation repair based on back translation plays an important role. If the users are unable to judge that a translated sentence is inaccurate, they do not undertake translation repair. Many inaccurate sentences are not repaired efficiently because of such inaccurate judgments by users. To avoid this inaccuracy of judgments, it is necessary to develop a method that measures the similarity between an input sentence and the back-translated sentence. This method can ensure that only accurate messages are exchanged between the users. However, some problems may occur with the use of this method, since it rejects the user's judgment. It is important to verify the efficiency of this method. We proposed a method that reduces the inaccuracy of judgment. If the method judges a message as inaccurate, the chat server does not send the message to the receiver and encourages the sender to rectify the sentence. We verified the efficiency of the proposed method in a chat communication using the Wizard of Oz method. The following conclusions can be drawn from the results of the experiments: (1) In this experiment, the chat communication progressed even if a user occasionally sent an inaccurate message. However, inaccurate messages disrupt communication. If our proposed method is applied, users can communicate with each other more accurately. Moreover, there were not any significant differences between the efficiency of communication with or without the proposed method. Therefore, our method can apply to the communication that is requires accuracy. (2) The proposed method made users uncomfortable because the proposed method denied their judgment and they did not know how they repair sentences. Therefore, it is not easy to apply the proposed method to chat communication simply.

Development and Evaluation of All-for-one Type Multilingual Conference Support System

吉野孝, 井出美奈（Part： Lead author )

情報処理学会論文誌 ( 情報処理学会 ) 51 ( 1 ) 36 - 44 2010.01 [Refereed]

近年，日本では非英語圏の在日外国人が増加してきており，母語が異なる人々の間で講義や会議をする機会が増加している．講義や会議の場において，外国人は内容理解に限界があると考えられる．そこで，聴講者である日本人が会議の内容を協力してまとめ，外国人の内容理解を支援する，All for one型多言語会議支援システムSAKINを開発した．SAKINの評価実験を行い，次の知見を得た．(1) アウェアネス情報の共有機能，発表スライドの利用機能は支援作業の負担を軽減できる．(2) 外国人からのフィードバック機能は多言語会議支援に有用であり，外国人の内容理解を助ける可能性がある．Non-English-speaking foreign residents of Japan have increased in these days, the opportunity of a lecture and a conference among people whose native language are different increases. There is a limitation in the content understanding at a lecture and a conference for foreigners. We have developed an All-for-one type multilingual conference support system SAKIN which supports contents understanding to compile content of a conference by Japanese participants. We performed an evaluation experiment using SAKIN, we obtained the following findings. (1) A function using a presentation slide and a sharing function of awareness information can reduce a burden of the support work. (2) A feedback function from a foreigner is useful for multilingual conference support and can help the contents understanding of the foreigner.

Development of circulating support environment of multilingual medical communication using parallel texts for foreign patients

Mai Miyabe, Taku Fukushima, Takashi Yoshino, Aguri Shigeno

World Academy of Science, Engineering and Technology 46 305 - 309 2010

The need for multilingual communication in Japan has increased due to an increase in the number of foreigners in the country. When people communicate in their nonnative language, the differences in language prevent mutual understanding among the communicating individuals. In the medical field, communication between the hospital staff and patients is a serious problem. Currently, medical translators accompany patients to medical care facilities, and the demand for medical translators is increasing. However, medical translators cannot necessarily provide support, especially in cases in which round-the-clock support is required or in case of emergencies. The medical field has high expectations from information technology. Hence, a system that supports accurate multilingual communication is required. Despite recent advances in machine translation technology, it is very difficult to obtain highly accurate translations. We have developed a support system called M3 for multilingual medical reception. M3 provides support functions that aid foreign patients in the following respects: conversation, questionnaires, reception procedures, and hospital navigation
it also has a Q&amp
A function. Users can operate M3 using a touch screen and receive text-based support. In addition, M3 uses accurate translation tools called parallel texts to facilitate reliable communication through conversations between the hospital staff and the patients. However, if there is no parallel text that expresses what users want to communicate, the users cannot communicate. In this study, we have developed a circulating support environment for multilingual medical communication using parallel texts. The proposed environment can circulate necessary parallel texts through the following procedure: (1) a user provides feedback about the necessary parallel texts, following which (2) these parallel texts are created and evaluated.

Verification of Improvement Effects of Translation Repair Efficiency Using Providing Inaccurately Translated Segments

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌 ( 情報処理学会 ) 50 ( 4 ) 1390 - 1398 2009.04 [Refereed]

機械翻訳を用いたコミュニケーションにおいて，翻訳リペアは不適切な翻訳箇所の少ない文章を作成する方法として重要な役割を果たす．一方，翻訳リペア作業はユーザに対して負担が大きく，コミュニケーションへ翻訳リペアを適用する場合，リペア効率の改善が不可欠である．リペア効率の改善手法の1つとして，翻訳不適箇所を指摘する手法が提案されている．従来研究では，精度向上の成功率や適切でない修正をした割合によって，翻訳不適箇所指摘の効果が評価されている．しかし，実際のコミュニケーションへの利用の観点から，修正時間などのコストに関する効率化が不可欠であり，翻訳不適箇所指摘の有効性を議論するためには，コストの軽減効果について検証する必要がある．そこで本論文では，翻訳不適箇所指摘を用いた翻訳リペア実験を行った．本実験では20文字以上30文字以下の文の翻訳リペアを行い，翻訳不適箇所指摘のリペア効率改善効果に関する考察により，以下の知見を得た．(1) 本実験では，翻訳不適箇所の指摘により，修正箇所の判定に関する学習期間の短縮効果が見られた．特に，低精度な折り返し翻訳文のリペアにおいて，提案手法による学習期間短縮の高い効果が見られた．しかし，この効果は大きなものではなく，リペア支援を行うためには翻訳不適箇所指摘以外の手法の検討が必要である．(2) 被験者の不正確判定率が適切な翻訳リペアの実施に影響している可能性が高く，不正確判定を減少させるための正確な文意一致判定の仕組みが必要であると考えられる．(3) 本実験では，コスト軽減の観点から，翻訳不適箇所指摘は大きなコスト軽減に貢献できず，翻訳リペア支援の効果は不十分であることを示した．Translation repair using back translation plays an important role in multilingual communication using machine translation. The cost of the translation repair is considerable high for the user. The support of efficient translation repair is required. Providing inaccurately translated-segments is presented as the method of improving translation repair efficiency. This method has been evaluated in the following views: the success rate of improving the translation accuracy and the rate of inadequate repair. However, the reduction of the translation repair costs, such as the repair time, is essential to apply the translation repair in actual communication. In the discussion of the effectiveness of providing inaccurately translated-segments, it is necessary to verify the improvement effects of translation repair cost using this method. We performed the experiment of translation repair to evaluate the effectiveness of providing inaccurately translated segments. In the experiment, we used the sentences that contained 20-30 letters. The results of the experiment are as follows. (1) For users who are inexperienced in translation repair work, the start time of the repair work is improved by providing translation inadequacy part. However, this improvement is not effective in actual communication. To support translation repair in actual communication, we need to develop more efficient methods. (2) The inaccurate-judgment rate can affect the improvement of the efficiency of translation repair. In order to reduce the inaccurate judgments, it is necessary to develop a method that measures the similarity between an input sentence and the back-translated sentence. (3) Providing inaccurately translated-segments cannot contribute to the reduction of the translation repair costs. Therefore, providing inaccurately translated-segments would be not effective to support the translation repair.

Evaluation of Interpersonal Acceptable Response Time in Real-time Remote Text-based Communication

宮部真衣, 吉野孝（Part： Last author )

情報処理学会論文誌 ( 情報処理学会 ) 50 ( 3 ) 1214 - 1223 2009.03 [Refereed]

テキストベースのリアルタイムコミュニケーションにおいて，メッセージ作成の長時間化は円滑なコミュニケーションを妨げる．コミュニケーションを円滑に行うためには，相手が許容できる時間内にメッセージ作成を終える必要がある．これまでに，システムの応答時間に関する人間の許容応答時間については明らかにされている．しかし，システムを介したテキストベースの対人リアルタイムコミュニケーションにおいて，相手の応答をどれだけ待つことができるのかについては明らかにされていない．本研究では，テキストベースのリアルタイム遠隔コミュニケーションにおける対人許容応答時間の評価を行う．評価実験では，対話状況を1対1での特に目的のない自由な対話とし，「相手の入力状況の提示」および「対話段階の進行」による対人許容応答時間への影響についての検証を行った．評価実験より，以下の知見を得た．(1) 対人許容応答時間は，平均で1分51秒であった．(2) 相手の入力状況を提示し，対話の序盤に測定するという条件下において，対人許容応答時間は平均2分35秒であり，相手の入力状況の提示により，対人許容応答時間が長くなる可能性が高い．(3) 対話の経過時間は，対人許容応答時間に対して大きな影響を及ぼさない可能性が高い．In text-based real-time communications, it may prevent smooth communications if typing a message requires a long time. A message must be sent with a duration that is acceptable to the other user involved in the communication. Other researches had discussed the range of system response times that would be acceptable to users. However, it has not been discussed yet the duration for which a user can wait for the other user's response. In this study, we evaluated the interpersonal acceptable response time in real-time remote text-based communication. In the experiment, we measured the interpersonal acceptable response time in casual one-to-one communication. We verified the effects of the providing of input status and the elapsed time of communication. Through our experiment, we obtained the following findings. (1) The average interpersonal acceptable response time is 1min 51 s. (2) The interpersonal acceptable response time is 2min 35 s when input status is presented to a user in an early phase of the communication. Therefore, providing input status has the effect of extending the interpersonal acceptable response time. (3) The elapsed time of communication does not significantly influence the interpersonal acceptable response time.

Development of Attendance Confirmation System AGENGO Using Hard-to-verbalize Images

吉野孝, 中濱誠司（Part： Lead author )

情報処理学会論文誌 ( 情報処理学会 ) 49 ( 7 ) 2722 - 2730 2008.07 [Refereed]

大学における出席確認の作業は比較的時間のかかる作業である．また，従来より，「代返」という行為が日常の講義で行われており，その対策が課題となっている．代返の確実な防止は教育効果の向上にもつながるが，確実な出席確認作業は，講義時間を圧迫するというジレンマもある．そこで，これらの問題を解決するために，短時間の出席確認が可能で，代返しにくい出席確認システムの構築を目指し，「言語化しにくい画像」に着目した出席確認システムAGENGOを開発し，実際の講義に適用した．AGENGOは，携帯電話を用いて画像を選択することで出席確認を行うシステムである．「言語化しにくい画像」に関する実験および実際の講義への適用の結果，次のことが分かった．( 1 )言語化しにくい画像の種類は画像の説明しにくさに影響を与える．類似画像の枚数（4枚～7枚）は，正解画像の説明しにくさに大きな影響を与えない，( 2 )AGENGOの講義への適用結果より，出席確認に要する時間は約4～5分である，( 3 )実際の運用においては携帯電話のトラブルへの対処が必須である，( 4 )「言語化しにくい画像」を用いたにもかかわらず，出席登録する際に取得しているログ（携帯電話の機種）から代返の可能性がある学生がいた，( 5 )特に言語化しにくい画像を出席画像としてAGENGOで使用すると，正解画像を識別できないという問題点が生じた．The task of attendance confirmation in a university is a comparatively timeconsuming one, and it may end up consuming the time allotted for lectures. Moreover, students often give “proxies,” also called as Daihen in Japanese, during lectures. The prevention of Daihen will increase attendance and therefore improvement the efficacy of education. The purpose of this study is to develop a short and difficult Daihen attendance confirmation system. We have developed an attendance confirmation system called AGENGO using hard-to-verbalize images. AGENGO is a system that confirms the attendance by selecting images using students' cellular phones. In this paper, we present an evaluation of hard-to-verbalize images and a trial of the system in actual lectures. From the results of the experiments and trials during actual lectures, we concluded the following. ( 1 ) The type of image influences the explanation of the image. The number of similar images does not influence the explanation of the image. ( 2 ) AGENGO required approximately 4窶骭5 min for attendance confirmation. ( 3 ) It is necessary to handle uncontrollable situations such as mobile phone breakdown, fluctuations in radio waves due to carriers, cellular phone models, and classrooms. ( 4 ) Even when we used hard-to-verbalize images, we found cases where students engaged in the practice of Daihen, as revealed by the AGENGO logs. ( 5 ) When we used very-hard-to-verbalize images, many students were not able to distinguish between a valid image and false images.

Language grid association: Action research on supporting the multicultural society

Satoshi Sakai, Masaki Gotou, Masahiro Tanaka, Rieko Inaba, Yohei Murakami, Takashi Yoshino, Yoshihiko Hayashi, Yasuhiko Kitamura, Yumiko Mori, Toshiyuki Takasaki, Yoshie Naya, Aguri Shigeno, Shigeo Matsubara, Toru Ishida

Proceedings - International Conference on Informatics Education and Research for Knowledge-Circulating Society, ICKS 2008 ( IEEE COMPUTER SOC ) 55 - 60 2008 [Refereed]

The Language Grid is a middleware with which people can connect and use language resources such as machine translations, morphological analyzers and others created in the fields of intercultural collaboration. The Language Grid cannot exist without the collaboration of Language Grid Users who provide language and computation resources, language services, and collaboration tools. This paper overviews Language Grid Association, a user group of the Language Grid and a body promoting action research to support the multicultural society. © 2008 IEEE.

DOI

折返し翻訳を用いた翻訳リペアの効果

宮部真衣, 吉野孝, 重信智宏（Part： Last author,　Corresponding author )

電子情報通信学会論文誌 D ( 電子情報通信学会情報・システムソサイエティ ) J90-D ( 12 ) 3141 - 3150 2007 [Refereed]

機械翻訳を用いた異文化間チャットコミュニケーションにおけるアノテーションの評価

藤井薫和, 重信智宏, 吉野孝（Part： Last author,　Corresponding author )

情報処理学会論文誌 48 ( 1 ) 63 - 71 2007 [Refereed]

Proposal and Evaluation of Pictograph Chat for Communication

MUNEMORI JUN, OHNO SUMIKA, YOSHINO TAKASHI

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 47 ( 7 ) 2071 - 2080 2006.07 [Refereed]

Pictographs have widely spread to add nuance to mails of mobile phones in Japan and foreign countries, e.g. China. We have developed a pictograph chat system, which can communicate each other using nothing but pictographs. We prepared 550 pictograph symbols. We applied the system for communication to 3 groups, which consist of the intimate friends group, the strangers group, and the Japanese students and foreign students group. The foreign students consist of Chinese (four persons), a Malaysian, and a Vietnamese. We have carried out experiences 18 times (six times in each experiment). We report the results of the experiments as below. (1) The subjects understood over 70% of the content of the very simple chat. (2) There seemed to be no difference between foreign students and Japanese students about the context of the chat and about the evaluation of the system. Japanese students tended to make the same context as foreign students. (3) Proper nouns should be prepared sufficiently. Proper nouns were used very well between intimate friends.

Development and Application of a Location-based Universal and Two-way Guide System xExplorer

MUNEMORI JUN, KAMISAKA DAISUKE, TRI THAI MINH, YOSHINO TAKASHI

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 47 ( 1 ) 28 - 40 2006.01 [Refereed]

There have been developed many guide systems using location information. But most of systems have one-way communication system. These systems don't aim to mutual communication between sightseers by information sharing. The two-way communication, such as a chat or exchanging digital files included photos, is a common sense in Japanese ubiquitous society. Therefore, we have developed a prototype universal guide system, which was named xExplorer. xExplorer has real-time information sharing functions including image data, a chat, and mutual location information. We applied the system to the streets in the southern bound of Osaka and the Palace museum in Beijing. Subjects were Japanese and Chinese. The results of experiments show below : (1) The evaluation of the image data sharing function was high in both Japanese and Chinese. Because they can share the others with view points in real timely. (2) The chat was used for not only communication but also explaining relating shared contents. Sometimes, the content of chat messages is about an image data. (3) The system should have a function that helps the correlation between image data and chats. Then, the image data, which is an object of chats, can be found easily. (4) It is necessary that image should be appended with other information such as the meeting point, etc.

Effects of Applying Multimedia Video Conferencing System to Intercultural Collaboration

MUNEMORI JUN, SHIGENOBU TOMOHIRO, MARUNO SHINJI, OZAKI HIROSHI, OHNO SUMIKA, YOSHINO TAKASHI

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 46 ( 1 ) 26 - 37 2005.01 [Refereed]

We have designed an intercultural teleconference system "RemoteWadaman III" and applied to presentations between Japan and China. RemoteWadaman III has the communication functions of text translation, a shared screen, shared pointers, a shared whiteboard, audio and video communication, a chat with pictograph. We use every function to understand about a presentation of partners. We carried out the experiment 8 times for measuring the effects of the multimedia support functions. We report the results of experiments as below. (1) The subjects thought that they understood about 70% of the content of the partner's presentation intuitively even if they didn't understand their partner's language. The rate of understanding was almost the same as they used English for discussion. (2) 59% of the sentence of chats has pictograph. Question mark and/or its pictograph existed about 17% of the whole sentence. 5% of the sentence consisted of only pictograph. These results suggested that pictograph could be used as supporting language of intercultural collaboration.

GUNGEN DX II : Idea Generation Support System with Grouping-labels Function for Hundreds of Labels

SHIGENOBU TOMOHIRO, YOSHINO TAKASHI, MUNEMORI JUN

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 46 ( 1 ) 2 - 14 2005.01 [Refereed]

We have carried out experiments using an idea generation support system, named GUNGEN, which supports the KJ method. We have used about one hundred labels in the experiments. Several hundred labels can improve the results of experiments in the KJ method. When we treat several hundred labels, we should understand all contents of them. We should equip a special function for understanding the content of labels. We have developed GUNGEN DX II, which has a special function for a lot of labels. We have carried out experiments using GUNGEN DX II. GUNGEN DX II have a special function named "the draft islands generating function" to support the KJ method which can handle hundreds of labels. The draft islands generating function supports the grouping-labels step of the KJ method by grouping labels easily. Each participant stacks similar labels dropping from the top of a window in order intuitively. The features of the function are to restrict a dropping time and to operate easily. The stacked labels of the same column become an island. Each participant performs the task individually. The function generates draft islands from the common part of each participant's islands automatically by majority decision. Participants make conclusive islands by correcting the arrangement of draft islands. We carried out the KJ method using hundreds of labels. We compared with results of experiments using GUNGEN. Even if the number of labels increased, the time required to group labels decreased about 30 percent.

Prototype of an emotional chat system using sense of touch

Hajime Yoshida, Takashi Yoshino, Jun Munemori

Digest of Technical Papers - IEEE International Conference on Consumer Electronics ( Institute of Electrical and Electronics Engineers Inc. ) 159 - 160 2005

We developed a prototype of a chat system using sense of touch. Depending on the power of grasping a mouse, two kinds of face marks ((∧∧), (&gt
&lt
)) are inputted to the chat window. We applied this prototype to a kind of an electronic conferencing system, named a remote seminar support system. From the results of experiments, we found that the system was effective for transmitting the tension to participants. We think this approach can be applied to various types of communication, for example, interactive TV with excitement level of audience. © 2005 IEEE.

DOI

NAMBA Explorer: A participative location-based city area information sharing system

Daisuke Kamisaka, Takashi Yoshino, Jun Munemori

Digest of Technical Papers - IEEE International Conference on Consumer Electronics ( Institute of Electrical and Electronics Engineers Inc. ) 459 - 460 2005

DOI

SEGODON-PDA: Flexible Lecture Support System Using Wireless LAN and PDAs

SHIGENOBU TOMOHIRO, NODA TAKAHIRO, YOSHINO TAKASHI, MUNEMORI JUN

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 45 ( 1 ) 255 - 266 2004.01 [Refereed]

We have developed a flexible lecture support system using PDAs and wireless LAN, named SEGODON-PDA. A conventional fixed lecture support system has been carried out only in the classroom such as a computer room. The problem is the trouble of management. PDAs are comparatively cheap and their portability is good. A flexible system can be built using PDAs. The system can support two types of lectures. We applied SEGODON-PDA to a lecture-type class. Students could download the contents for the lecture using a wireless LAN in class and could write something on a blackboard while carrying and seeing a PDA. They could do their homework outside of the classroom. We applied SEGODON-PDA to an exercise-type class. Students could collect ideas for the exercise of an idea generation method. They make a presentation about results of the exercise using their PDA with a wireless LAN. We have applied the system for third year students. The results of the applications are shown below. (1) The results of the application show that SEGODON-PDA is effective and highly evaluated. The class became interactive between the lecturer and students. (2) The system could support several types of lectures. The system could also support the homework or the preparation outside of the classroom.

Development and Application of a Weakly Sense of Solidarity Support System with Semi-automatic Self-declaration Function of Situations

MUNEMORI JUN, MORI NAOTO, YOSHINO TAKASHI

IPSJ journal ( Information Processing Society of Japan (IPSJ) ) 45 ( 1 ) 188 - 201 2004.01 [Refereed]

We have developed a weak-collaboration system. which shared situation information of each participant. named "hima-hima notes". Participants had forced to input the information into the system themselves manually. The load of input for the participants would be very high and then the information providing of the system would become to poor situation. We modi-fied the "hima-hima notes" and the system could provide the semi-automatic self-declaration of situation. The system forces to input participants' situation between constant periods automatically. The system decides the situation of participants based on their response time automatically. We also provide our original parameter of situations named 'himado'. The 'himado' means the ratio of the spare time. We applied the system. The results of experiments show below : The semi-automatic self-declaration function of 'himado' was effective for a weak-collaboration. The semi-automatic self-declaration became trigger to active for participants. The function must occur to increase the action, for example, the browsing other participants' situation or writing the shared white board or self-declarations of their situations.

GDA: A Combined or Shared Screen System Based on Several PDAs

NODA TAKAHIRO, YOSHINO TAKASHI, MUNEMORI JUN

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 44 ( 10 ) 2478 - 2489 2003.10 [Refereed]

PDAs (Personal Digital Assistants) have spread widely. Radio network technology, such as wireless LAN, has also spread widely. There are many systems that support cooperative work using the latest advanced environment. However, it is difficult to do cooperative work smoothly on a PDA because the screen of a PDA is too small. Then. we have developed GDA (Group Digital Assistant). GDA can combine or share screens of PDAs. Vve experimented in cooperative work using KJ method support application that operates on GDA. We found the followings from the results of the experiments. (1) Users used combined screen of PDAs for large workspace effectively. Users used shared screen of PDAs when one of two persons mainly operated a PDA and the other advised an operating person. (2) Users changed a combined screen and a shared screen at a cooperative work frequently.

Group Digital Assistant: Shared or combined PDA screen

T Yoshino, T Noda, J Munemori

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS ( IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC ) 49 ( 3 ) 524 - 529 2003.08 [Refereed]

This paper proposes a new concept of a shared and combined screen for new small devices called GDA (Group Digital Assistant). In the GDA, the screens of two PDAs can be shared at a sharing view mode, and can be treated just like one screen at a combination mode. The GDA uses a wireless LAN and Bluetooth for radio communication. We have developed application software and experimented in cooperative work for evaluation. We found that functions of the GDA were effective in actual cooperative work. The concept of the GDA can make flexible usage of a cellular phone and a PDA in the next generation.1.

Development of a Real-time Four-frame Strip Cartoon Creation Support System for Many People

KAJITA KOUHEI, YOSHINO TAKASHI, MUNEMORI JUN

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 44 ( 2 ) 317 - 327 2003.02 [Refereed]

Most of work of drawing a picture have been performed by one person. A realtime and cooperation work could be easily performed by the spread of networks. Then, we have develoved a real-time four-frame strip cartoon creation support system AB-DOKAN. AB-DOKAN is a support system for the four-frame strip cartoon creation by a few people in real time. A four-frame strip cartoon is originally drawn by one person. If comics can be drawn by many people, we can share the processes of the four-frame strip cartoon. Handwritten comics creation without computers were also performed by one person for comparatively. Consequently, we found that the four-frame strip cartoon was able to be created by a few people. The comics created by three persons take more time than by one person, but the contents tend to be interesting. Because three persons draw each frame and they think the last frame cooperatively.

Development and Application of Electronic Tag-playing Support Groupware with Awareness Support Functions

YOSHINO TAKASHI, YOSHINAGA TAKAFUMI, MUNEMORI JUN （Part： Lead author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 44 ( 2 ) 297 - 308 2003.02 [Refereed]

Mobile phone, PHS and PDA (Personal Digital Assistant) are highly portable, and positioning data will become important data for human communication. There are many location-aware services. However, most of services only transmit or display a partner or the position information on target as a map. There was no service using the sense of hearing or touch as expression of position information. Then, we have developed the electronic tag-playing support groupware with awareness support functions. We performed experiments 30 times with the awareness support functions and without the awareness support functions at two universities. The results of the experiments were showd below. (1) We found that the evaluation of interesting was improved by awareness support functions and additional map information. (2) It is necessary to change the method of awareness support corresponding to the size of the place of an experiment. (3) The awareness support functions are more effective by the increase in the number of times used.

Application and Evaluation of Distributed Remote Seminar Support System RemoteWadaman II over Two Years

YOSHINO Takashi, MUNEMORI Jun （Part： Lead author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 43 ( 2 ) 555 - 565 2002.02 [Refereed]

We have developed a real-time distributed remote seminar support system, named RemoteWadaman II. The system can connect several computers via the Internet. Each student can operate his or her own computer. This system uses the following two communication methods. The first method is for large amount data and asynchronous information using a file server. The second method is for shared cursors and a shared screen using a direct communication by the mesh-type network. We developed functions to send and receive a file all over a seminar for the increase in efficiency of a seminar. RemoteWadaman II was applied seminars between two Universities 55 times and estimated by log analysis and questionnaires. Each participant was seen a shared report and shared cursors on his or her own PC, and each participant was able to use a chat. The number of sheets of a report increased by the functions to send and receive a file after a seminar start. As the result, this system has improved both the quality and quantity of a seminar.

The prototype of brain model hyper communication mechanisms

Jun Munemori, Takashi Yoshino

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 232 - 233 2002

We propose a new communication technique, which is named the brain model hyper communication mechanism for group-ware. The mechanism mimics the brain processing. The sending mechanism sends almost all kinds of data of environment. The receiving mechanism integrates and processes the data selectively and hierarchically. We developed the prototype based on the mechanism and applied it to a collaboration game. The prototype has video, voice, and the touch of sense communication channels. The results of experiment were evaluated comparatively high value when we used the touch of sense detection system.

GDA: A flexible personal digital assistant that combines the screen of PDAs and their radio communication methods

Takahiro Noda, Takashi Yoshino, Jun Munemori

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics 1 300 - 305 2002

We proposed a new concept that combines the screen of a PDA flexibly and that can flexibly choose the radio communication methods. We have developed the prototype of the system, called GDA. The screens of two or more PDAs can by treated just like one screen. That is, two or more screens of PDAs are flexibly combinable depending on the situation. As radio communication methods, GDA can choose PHS data communications and wireless LAN freely depending on the situation. We considered application to an idea generation support system. We performed the KJ method using the GDA. The KJ method with a GDA obtained relatively good evaluation from the results of the questionnaire.

Movable lecture support system using PDAs

Jun Munemori, Takashi Yoshino, Atsushi Yoshida

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics 1 294 - 299 2002

We have developed a movable lecture support system using PDAs and wireless LAN, named SEGODON-PDA. We have applied the system lectures of third year students. The results of the application show that SEGODON-PDA (with wireless LAN) is very effective and highly evaluated, because students can download the contents for the lecture using the wireless LAN in class and can write something on the blackboard while carrying and seeing the SEGODON-PDA. The class became interactive between the lecturer and students.

Development and Application of the Electronic Playing Tag Support Groupware

MUNEMORI Jun, MIYAUCHI Emi, MUTA Tomohiro, YOSHINO Takashi, YUNOKUCHI Kazutomo

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 42 ( 11 ) 2584 - 2594 2001.11 [Refereed]

PDA(Personal Digital Assistant)is highly portable, and the positioning data will become important data for a PDA. There are many location-aware services. But most of services using PDAs and GPSs are one-way services. So, we should develop two-way interaction services. That is, the services that clients of the system should move freely and get and present location information of other clients easily. We have developed the electronic playing tag support groupware. The system consists of a PDA, a GPS and a mobile phone. We performed five types of experiments at two universities 24 times. Four types are the electronic playing tags and the remainder is a conventional playing tag. One of the experiments can realize participation between remote universities. The results of experiments were showed below. (1) The devised services based on the electronic playing tag support groupware were better estimation than that of the conventional playing tag. The mutual positioning information using a GPS was effective for the playing tags. (2)If the accuracy of a GPS decrease, we spend a little more time to catch. But the time did not exceed the playing time of the conventional play tag. (3)We can realize the electronic playing tag between remote universities. But we should add the fealty using the remainder of five sense for lack of seriousness.

A Spiral-type Idea Generation Method Support System for Sharing and Reusing Knowledge and Information Among a Group

Takashi Yoshino, Jun Munemori, Tomohiro Shigenobu, Kazutomo Yunokuchi （Part： Lead author,　Corresponding author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 41 ( 10 ) 2794 - 2803 2000.10 [Refereed]

We have developed an idea generation support system, called GUNGEN-Spiral. GUNGEN-Spiral supports collecting ideas, saving ideas, sharing ideas, shaping ideas and reusing ideas. The system consists of GMemo running on a Personal Digital Assistant(IBM WorkPad), Wadaman(Whole mediA DAta MANagement system), WWWW(World Wide Web Wadaman, W4)and GUNGEN(GroUpware for a New idea GENeration consistent support system). Users can collect and input ideas in free handwriting using GMemo immediately anytime and anywhere, and the ideas are saved in Wadaman and shared all together using W4 on the Internet. Moreover, participants use those ideas directly as data for GUNGEN. We can reuse the results of GUNGEN as topics for further ideas, and others' ideas sometimes give rise to new ideas. We have applied this system on a trial basis.

Development and Application of a New Idea Generation Consistent Support System with Personal Digital Assistants

YOSHINO Takashi, MUNEMORI Jun, YUNOKUCHI Kazutomo, IZUMI Yutaka, UEHARA Tetsutaro, YOSHIMOTO Fujiichi （Part： Lead author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 41 ( 9 ) 2382 - 2393 2000.09 [Refereed]

We have developed data collecting software, called GMemo(GUNGEN Memo), running on a Personal Digital Assistant(PDA). GMemo is a piece of input equipment foe GUNGEN. GUNGEN is a groupware for a new idea generation consistent support system. Users can collect data for the KJ method using GMemo easily with no omission, and input ideas in free handwriting. we thought that such sudden ideas need to be stored in anytime and anywhere. The feature of GMemo is using handwriting data as input data for GUNGEN directly. We requested members of the Wakayama University Information Science Center to use GMemo regularly. They have used GMemo for about five months. The kinds of collected data were about the improvement of centers works and the improvement of GMemo. We carried out KJ method using handwritten data collected by GMemo. In this paper, we describe the result of the data collection using GMemo and the result of KJ method using handwritten data collected by GMemo. Furthermore, we show the effectiveness of the data collection using PDA.

Application of Distance Learning Support System SEGODON to Exercise - type Classes

Takashi Yoshino, Jun Munemori, Takaya Yuizono, Yoji Nagasawa, Shiro Ito, Kazutomo Yunokuchi （Part： Lead author,　Corresponding author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 40 ( 11 ) 3946 - 3956 1999.11 [Refereed]

We have developed a distance learning support system called SEGODON for exercise-type classes, and applied this system to "Applied Mathematics Exercise" classes four times, continuously. The system consists of 40 personal computers, a workstation and inexpensive input equipment. A teacher can conduct an exercise-type class with students via a network. We developed a report submission system to conduct exercise-type classes. A student can submit a report to a teacher during class, and the teacher can mark the report and return it to the student. We have solved problems of applications to exercise-type classes and have developed the necessary functions for the "Applied Mathematics Exercise". We found the following results from these applications. (1) The distance learning class (exercise) using SEGODON was as effective for the students as the normal class (exercise). (2) We found that the treatment of reports was important in an exercise-type class. We found that the maximum number of submitted reports that could be checked by a teacher and a TA was approximately 70. (3) We found that special functions for the exercise, i.e., the expression input support palettes, were required.

Development of a Multi - user Electronic Conferencing System : DEMPO III

YOSHINO Takashi, MUNEMORI Jun, ITO Shiro, NAGASAWA Yoji （Part： Lead author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 40 ( 1 ) 150 - 160 1999.01 [Refereed]

We have developed a multi-user electronic conferencing system, named DEMPO III. DEMPO III is a text-based desktop electronic conferencing system for a face-to-face environment. This system was implemented in a network in our program-practicing room, consisting of 40 personal computers and one workstation. Most systems for multiple users have a chat function, but there are few real systems that can move opinion labels on the screen freely. We have developed an electronic conferencing system that can represent opinions among large numbers of people. The system has two distinctive methods, as follows: First, all recorded information is stored under a file name but not in file contents. Secondly, access from personal computers to the workstation is performed by the use of FTP at a constant interval. We have applied this system to actual conferencing 6 times with more than 10 people, and some functions, especially opinion labels freely moving function, have received a favorable reception by the users. The experiments using 40 computers showed the stable acquisition of data.

AMeDASデータを利用したマルチビーム型衛星放送における増力ビームの選択方法

吉野孝, 伊藤士郎

電子情報通信学会論文誌. B, 通信 = The IEICE transactions on communications. B / 電子情報通信学会編 ( 電子情報通信学会通信ソサイエティ ) 82 ( 1 ) 64 - 70 1999.01

Development and Application of a Supporting System for Distance Learning Classroom Using Personal Computers via Internet

YOSHINO Takashi, INOUE Yutaka, YUIZONO Takaya, MUNEMORI Jun, ITO Shiro, NAGASAWA Yoji （Part： Lead author )

Transactions of Information Processing Society of Japan ( Information Processing Society of Japan (IPSJ) ) 39 ( 10 ) 2788 - 2801 1998.10 [Refereed]

We have developed a supporting system for distance learning classrooms via Internet, which can consist of 40 personal computers and inexpensive input equipment. This system may support a classroom, in which a teacher lectures for students in a remote computer practicing room. In the teacher side, a picture of the classroom is always displayed by a remote control camera, and the upper half of the teacher's body is always seen on a screen in the classroom. For questions and answers a direct connection between the teacher and any student in the classroom can be set up for video and audio signals. Additionally, this system is equipped with shared cursors between a teacher and students, a blackboard system and a note system. Three kinds of distance learning classrooms have been tried; (1) between Osaka University and Kagoshima University, (2) between two buildings in Kagoshima University, and (3) within a computer practicing room. In these applications, it has been found that better understanding may be performed for students by this system.

Development of Educational Platform DEMPO II and Its Application to Programming Exercise

YOSHINO Takashi, MUNEMORI Jun, ITO Shiro, NAGASAWA Yoji （Part： Lead author )

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 37 ( 5 ) 891 - 901 1996.05 [Refereed]

Recently, it has been actively studied that a support system for advanced education that is mixed some of groupware, multimedia, and hypertext. However, being closely related them each other, it is necessary to build a software platform for computers. So, we have developed an educational platform named DEMPO II. DEMPO II consists of an electric conference system, a question-answer system, a progress report system, an e-mail system, a database with distribution link, a file system with 3D like visual interface, and a distributed computer managing system. We have used this system for programming exercises and we found various things. We describe merits, demerits, and future specification of DEMPO II in this paper.

Development of a Distributed Multimedia Platform and Its Application to Intellectual Cooperative Works

MUNEMORI Jun, YOSHINO Takashi, NAGASAWA Yoji

IPSJ Journal ( Information Processing Society of Japan (IPSJ) ) 34 ( 6 ) 1385 - 1394 1993.06 [Refereed]

A distributed multlmedia platform, DEMPO, has been developed for studying next generation of computer software environment. DEMPO consists of WildCard, Emc, and Wadaman. WildCard based on a desktop system manages the whole system and permits a 3-D screen display. Emc is an electronic meeting system having an extra function to take in chats on the way of meeting. Wadaman is an intellectual productive work support system based on HyperCard. DEMPO was implemented on a computer system for student education and applied to a programming exercise of students with satisfactory results.

　PREV-NEXT　

<YOSHINO Takashi>

Published Papers - YOSHINO Takashi