現在、または過去に行った研究の一部を紹介をします。

（科学研究費データベース内のリストを参照して下さい）

教育ビッグデータを用いた教育・学習支援のためのクラウド情報基盤の開発

本研究では、「教育ビッグデータ」、「クラウド情報基盤」、「教育データ科学」に関する以下の3つの目的を達成するために研究を行います。

• デジタル教科書やe-Learning等を用いてフォーマル(講義内)、インフォーマル(講義外)な学習を両方含め、生涯にわたる学習ログ (Learning Logs) を蓄積し、教育ビッグデータを構築
• そのデータを分析して、教育・学習をサポートする教育用クラウド情報基盤を創出
• 「教育データ科学」の学問領域を創設してデジタル時代の「学び」を解明し、新しい教育・学習環境を創造する

本研究では教育データ科学を創設しますが、そのためのデータを収集・分析するために、教育クラウド情報基盤を構築します。

教育クラウド情報基盤により、学校教育などのフォーマルな学習と家庭学習などのインフォーマルな学習の双方において、デジタル教科書やe-Learning、データ分析などのツールを提供して、教育ビッグデータの蓄積と利活用をシームレスに支援可能です。

なお、本研究は、日本学術振興会 科学研究費助成事業 基盤研究(S)の補助を受けています。

詳しい情報は、こちらのページをご覧下さい。

ラーニングログを用いたユビキタス学習環境の研究

本研究では、次世代のe-Learning環境として、日常生活での学習の体験映像をラーニングログとして蓄積し、他の学習者と共有することで、知識やスキルの獲得を支援する、ユビキタス学習の情報基盤を開発し，大学などで実践を行い評価します。特に、その場所や時間など学習者の周囲の状況に適した情報を学習者に知らせ、学習者の環境やニーズと調和して適切な情報コンテンツを提供し、学習プロセスを支援する学習環境の構築を目指します。

なお、本研究は、JSTさきがけ、及び、日本学術振興会 科学研究費助成事業 基盤研究(B)の補助を受けています。

詳しい情報は、こちらのページをご覧下さい。

Research on Ubiquitous Learning

本研究の目的は，ワイヤレス・モバイル端末を用いたユビキタスコンピューティング環境において，学習者個人個人にあった形で，適応的に日常的な学びを支援するユビキタス協調学習環境のフレームワークをデザインし，実際にシステムを開発・評価することです．特に，学習者中心の学習デザインに立ち，いつでもどこでも(anytime and anywhere)利用できる学習環境を提供するだけでなく，適切な場所で適切な時に適切な教材や解決方法，並びに協調学習のきっかけを与える学習環境RTRPL(Right Time and Right Place learning)を目指しています。

TANGO: Vocaburary Learning with RFID tags

suports to link phisical objects and vocaburaries with RFID tags.

JAPELAS

helps to learn Japanese polite expressions by detecting users' social relationships etc.

JAMIOLAS

helps to learn Japanese omomatopoeia with Phigedts sensors.

過去の研究プロジェクト

• デジタル教材の学習履歴を中心とした教育ビッグデータの利活用アプリケーションの研究開発（NICT委託研究@九州大学）
• ティーチングポートフォリオの開発と導入（九州大学学内EEPプロジェクト）

Sharlok: Computer Supported Collaborative Learning Environment

Knowledge awareness (KA) has been proposed to increase collaboration opportunities in an open ended and collaborative learning environment. To encourage collaboration, an individual user’s agent called KA-Agent autonomously informs the learner about up-to-the-minute activities from other learners. For instance, a message might be “someone is looking at the same knowledge that you are looking at.” Although this message, called active KA, is very useful to create real-time collaboration, a large number of messages often confuse learners and disturb their learning. Therefore, the agent has to have an information filtering facility to inform a learner of the important messages of KA. This paper describes a KA filtering technique based on some educational strategies toward efficient collaborative learning.

CoCoA: Computer Supported Collaborative Correction Environment

CoCoA (Commutative Collection Assisting System) is a computer-mediated language-learning environment that supports students and teachers to exchange marked-up documents via Internet. Its environment is very similar to a real one in which people use paper and pen. CoCoA allows teachers not only to correct the compositions sent from foreigners by E-mail, but also learners to see where and why the teacher corrected them. CoCoA improves the opportunities that foreigners have for writing Japanese compositions and for receiving instructions from teachers. In order to record and exchange corrected compositions with some marks and some comments, this paper also proposes CCML (Communicative Correction Mark-up Language), which is based on XML.

PeCo: Computer Supported Social Networking Environment

Beyond the information stored in pages of the World Wide Web, a type of ``meta-information'' is created when they connect to each other. This new information is a collective effect of independent users writing and linking pages, hidden from the casual individual user. Accessing it and understanding the inter-relation of community and content in the WWW is a challenging problem to form a new community or join an exiting community in social creativity & lifelong learning. We have developed a prototype system called “community-finder”, which visualize topic-specified relationships can be precisely located by looking only at the graph of hyperlinks, gleaning content and context from the Web without having to read what is in the pages. Noting that reciprocal links (co-links) between pages signal a mutual recognition of authors. In addition, the system detects the central person based on social network analysis. The central person means the mainly active contributor in the community. The user might obtain much information from the center person about the keywords that the user gave as well as from the web page of the center person. Moreover, social network represented with direct graph shows the access to the center person.

Neckle: Network based Communicative Kanji Learning Environment

This project focuses on the problem of language transfer in foreign language learning. The transfer caused by the difference between learner’s mother language and target language, often leads a communicative gap. This paper first analyzes the semantic relations between learner’s mother language and target language. Then proposes a CGM (Communicative Gap Model) due to language difference. We have developed a communicative language-learning environment called Neckle (Network-based Communicative Kanji Learning Environment) to support foreign language learning through communication with native speakers. Neckle has a software agent called Ankle (Agent for Kanji Learning). Ankle observes the conversation between the learner and the native speaker, checks up the communicative gap according to CGM, and notices the gap for the support of language learning congenial to each learner. Learners can not only be aware of the language difference but also acquire its cultural background from the native speakers.