• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Developing methods and environments to stimulate pre-readers' reading habit by using SNS

Research Project

Project/Area Number 16K12542
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Library and information science/Humanistic social informatics
Research InstitutionThe University of Tokyo

Principal Investigator

KAGEURA KYO  東京大学, 大学院情報学環・学際情報学府, 教授 (00211152)

Research Collaborator YADA Shuntaro  
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
KeywordsTwitter / 感情要因 / 触発性 / データアノテーション / 図書に言及するツイート / 態度分析 / 強迫性 / 誘引性 / 談話分析 / 文書分類 / 固有表現抽出 / 書名 / 教師付き学習 / 情報サービス / 読書触発 / SNS
Outline of Final Research Achievements

We developed two-step method to identify Tweets that mention Books (TMBs). The method assumes the existence of comprehensive catalogue of book titles and defined the identification task as classification task. Our method achieved practical level precision and the evaluation suggested that our method is comparable to SOTA method in a related task of spam/bot detection.
To identify stimulating tweets (attracting readers and non-imposing), we developed a ML-based method. To facilitate learning, we constructed datasets with a series of tags that indicates the degree of stimulation that TMBs have. An evaluation experiment with over 30 human evaluation participants show that what we judge as "stimulating" tweets are significantly more stimulating than randomly chosen tweets.
Currently we have a prototype system that entice pre-readers into reading, which is under updating. We will make the experimental system available in AY2019.

Academic Significance and Societal Importance of the Research Achievements

街の書店が激減する中、消極的に図書に触れる機会が減っている。オンライン上では積極的に関心を向けた場合には多様な図書関連情報が得られるが、それは既に読書習慣を身につけた人にとって有効ではあるものの、「前読書家」には有効ではない。本課題は、しばしば日常的な文脈で友人や知人・家族等から消極的に得られる図書関連情報が一定程度、人を読書及び図書選択に導くことを踏まえ、それに対応した機構をSNS上で実現しようとするもので、多くの読書関連サイトが読者を想定しているのに対し「人が読むようになることを促す環境」を構築するという点で独創的であり、また、社会的な重要性も高い。

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (11 results)

All 2019 2018 2017 2016 Other

All Int'l Joint Research (3 results) Journal Article (1 results) (of which Peer Reviewed: 1 results,  Acknowledgement Compliant: 1 results) Presentation (7 results) (of which Int'l Joint Research: 3 results)

  • [Int'l Joint Research] Data 61, CSIRO(オーストラリア)

    • Related Report
      2018 Annual Research Report
  • [Int'l Joint Research] CSIRO Data 61(オーストラリア)

    • Related Report
      2017 Research-status Report
  • [Int'l Joint Research] Calvin College(米国)

    • Related Report
      2017 Research-status Report
  • [Journal Article] Improved Identification of Tweets that Mention Books: Selection of Effective Features2016

    • Author(s)
      Shuntaro Yada and Kyo Kageura
    • Journal Title

      ICADL

      Volume: 18 Pages: 150-156

    • DOI

      10.1007/978-3-319-49304-6_19

    • ISBN
      9783319493039, 9783319493046
    • Related Report
      2016 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Presentation] 図書を推薦するツイートの押し付けがましさに関する特徴の分析2019

    • Author(s)
      矢田竣太郎, 影浦峡
    • Organizer
      言語処理学会第25回年次大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 論文において外部の資料を引用・参照している文の特徴2018

    • Author(s)
      渡邊 晃一朗, 矢田 竣太郎, 影浦 峡
    • Organizer
      言語処理学会第24回年次大会
    • Related Report
      2017 Research-status Report
  • [Presentation] 日本語書籍タイトルの形式的構造の分析2017

    • Author(s)
      矢田竣太郎, 岩井美樹, 影浦峡
    • Organizer
      言語処理学会第23回年次大会
    • Place of Presentation
      筑波大学(茨城県つくば市)
    • Year and Date
      2017-03-14
    • Related Report
      2016 Research-status Report
  • [Presentation] A bootstrap method for automatic rule acquisition on emotion cause extraction2017

    • Author(s)
      Shuntaro Yada, Kazushi Ikeda, Keiichiro Hoashi and Kyo Kageura
    • Organizer
      ICDM Sentire Workshop
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Measuring discourse scale of tweet sequences: A case study of Japanese Twitter accounts2017

    • Author(s)
      Shuntaro Yada and Kyo Kageura
    • Organizer
      ICADL 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Twitter content eliciting user engagement: A case study on Australian organisations2017

    • Author(s)
      Sunghwan Mac Kim, Kyo Kageura, James McHugh, Surya Nepal, Cecile Paris, Bella Robinson, Ross Sparks, Stephen Wan
    • Organizer
      WWW 2017 Poster Session
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] 図書に言及するツイートの抽出: 素性・データ量・手法の効果に関する考察2016

    • Author(s)
      矢田竣太郎, 影浦峡
    • Organizer
      電子情報通信学会言語理解とコミュニケーション研究会
    • Place of Presentation
      小樽商科大学(北海道小樽市)
    • Year and Date
      2016-06-04
    • Related Report
      2016 Research-status Report

URL: 

Published: 2016-04-21   Modified: 2022-02-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi