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

Detecting, predicting, and deterring fake news using information-sharing models

Research Project

Project/Area Number 21K11883
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60070:Information security-related
Research InstitutionThe University of Electro-Communications (2023)
Kyoto Tachibana University (2021-2022)

Principal Investigator

Yoshiura Hiroshi  電気通信大学, その他部局等, 名誉教授 (40361828)

Co-Investigator(Kenkyū-buntansha) 佐藤 寛之  電気通信大学, 大学院情報理工学研究科, 准教授 (60550978)
Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2023: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywordsフェイクニュース / 誤情報 / 検知 / 拡散予測 / 社会分断 / 偽情報 / 情報共有モデル / ニュース信頼度 / 社会分断緩和 / 拡散モデル / ユーザ説得 / 分断緩和 / ユーザ間信頼度 / 予測 / 対策
Outline of Research at the Start

情報共有モデルを用いたフェイクニュースの検知、伝搬予測および対策を研究する。具体的には、ネットワークにおけるフェイクニュースの共有を表現するモデルを確立し、このフェイクニュース共有モデルを用いて、ニュースの伝搬データを解釈することで当該ニュースの真偽を推定すると共に、各ユーザのニュースを信じる度合等を推定可能とする。また、上記のモデルを用いてフェイクニュースの将来の広がりを推定可能とし、その対策を可能とする。

Outline of Final Research Achievements

Fake news cause serious problems in modern society. Conventional countermeasures could be circumvented by knowledgeable fake news writers. In addition, network users did not accept even correct detection of fake news due to the backfire effect. We proposed countermeasures based on models representing how information disseminates among network users. Our proposed methods conform news dissemination simulated on the models to real dissemination data by optimizing the model parameters. The proposed methods estimate reliability of news as well as belief of network users based on the optimized parameters, and estimate future dissemination of fake news by continuing the simulation.

Academic Significance and Societal Importance of the Research Achievements

情報共有モデルを用いたフェイクニュース検知は従来研究されていない。提案法は、ニュースとユーザの全体的な関係に基づくため回避が困難であり、モデルに手続き的なプログラムを組み込み可能であるため拡張性が高い。フェイクニュース対策の最も困難な課題は、ユーザが真実を受け入れないことであるが、提案法は、モデルのパラメータ値からネットワークユーザの心理状態を推定し、この問題への対策の基礎情報を得ることができる。また、従来研究されなかったフェイクニュースの拡散予測をモデル上で初めて可能にした。フェイクニュースの拡散は極めて深刻な社会問題であり、本研究の社会的意義は大きい。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (5 results)

All 2024 2022 2021

All Presentation (5 results) (of which Int'l Joint Research: 5 results)

  • [Presentation] Explainable Multimodal Fake Posts Detection Using Feature Extraction with Attention Mechanisms2024

    • Author(s)
      Tomoaki Ohkawa, Hiroshi Yoshiura, Takayasu Yamaguchi
    • Organizer
      IEEE International Workshop in Cyber Forensics, Security, and E-discovery (CFSE 2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Breaking Anonymity of Social Media by Profiling from Multimodal Information2022

    • Author(s)
      Eina Hashimoto, Masatsugu Ichino, Hiroshi Yoshiura
    • Organizer
      IEEE International Workshop in Cyber Forensics, Security, and E-discovery
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Modeling Malicious Behaviors and Fake News Dissemination on Social Networks2021

    • Author(s)
      Kento Yoshikawa, Masatsugu Ichino, Hiroshi Yoshiura
    • Organizer
      IFIP Conference on e-Business, e-Services and e-Society (I3E2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Maintaining Soundness of Social Network by Understanding Fake News Dissemination and People's Belief2021

    • Author(s)
      Risa Kusano, Kento Yoshikawa, Hiroyuki Sato, Masatsugu Ichino, Hiroshi Yoshiura
    • Organizer
      International Workshop on Informatics (IWIN2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Reliability-Disguised Attacks on Social Network to Accelerate Fake News Dissemination2021

    • Author(s)
      Kento Yoshikawa, Takumi Awa, Risa Kusano, Masatsugu Ichino, Hiroshi Yoshiura
    • Organizer
      IEEE International Workshop in Cyber Forensics, Security, and E-discovery (CFSE 2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi