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

Estimating Extensive Reading Text Difficulty Using Machine Learning

Research Project

Project/Area Number 20K00800
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 02100:Foreign language education-related
Research InstitutionShinshu University

Principal Investigator

Brierley Mark  信州大学, 全学教育センター, 外国語准教授 (70646877)

Co-Investigator(Kenkyū-buntansha) 新村 正明  信州大学, 学術研究院総合人間科学系, 教授 (20345755)
RUZICKA DAVID (RUZICKA DAVID・ED)  信州大学, 学術研究院総合人間科学系, 准教授 (70436898)
長谷部 めぐみ  信州大学, 学術研究院総合人間科学系, 准教授 (50878725)
Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords多読 / 難易度 / 機械学習 / 難易度推定
Outline of Research at the Start

多読とは,文章を分析しながら読むのではなく大意を把握するような読み方,いわゆる通読により多量の本を読むものであり,読解力や語学能力を高める学習方法として利用され,多くの教育的効果があることが報告されている.
この多読の学習効果を高めるために,学習者は適切な難易度の多読図書を選択する必要がある.このため,出版社や多読支援団体が,図書毎に難易度を定めているが,それぞれが異なる評価を行っており,統一された難易度とは言い難い.
そこで本研究では,実際の運用で蓄積された学習者による難易度評価や図書に含まれる単語の種類等のデータ等を機械学習し,多読図書の難易度を自動推定するシステムの開発を行う.

Outline of Final Research Achievements

We have developed an extensive reading support system and accumulated a substantial amount of data over more than 10 years of operation. This study investigated a method for automatically estimating the difficulty of extensive reading materials using machine learning. Utilizing the accumulated data, we iteratively selected machine learning techniques and formatted data to improve the method's accuracy. The experimental results confirmed the effectiveness of this method, suggesting it as a valuable tool for extensive reading learners.

Academic Significance and Societal Importance of the Research Achievements

本研究では、多読図書の難易度を自動推定するシステムの開発に向けた基礎研究を行い、難易度のパラメータを解明しました。学術的には、多読学習の効果を定量的に評価する新しい知見を提供しました。社会的には、学習者が適切な難易度の図書を選択することで、語学力の向上を支援し、教育の質を高める可能性があります。この研究は、教育機関や公共図書館での応用が期待されます。

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (15 results)

All 2023 2022 2021 2020

All Journal Article (3 results) (of which Peer Reviewed: 2 results,  Open Access: 2 results) Presentation (12 results) (of which Int'l Joint Research: 3 results,  Invited: 2 results)

  • [Journal Article] Reading The Gruffalo in Another Language: Assessing Non-Graded Children’s Picture Books for Extensive Reading2023

    • Author(s)
      Corinna V. GOTO & Mark BRIERLEY
    • Journal Title

      信州大学総合人間科学研究

      Volume: 17 Pages: 92-104

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Teaching Academic English in the Age of AI: Notes on What Translation Software Means for University English Education2021

    • Author(s)
      Ruzicka, David
    • Journal Title

      Shinshu University Journal of Arts and Sciences

      Volume: 15 Pages: 133-145

    • NAID

      120007144854

    • Related Report
      2020 Research-status Report
  • [Journal Article] Developing an Online Graded Reader Database to Support ER2020

    • Author(s)
      Mark Brierley, Ryoma Nakamura, Masaaki Niimura
    • Journal Title

      Proceedings of the fifth World Congress of Extensive Reading

      Volume: 5 Pages: 219-228

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] 一般図書の英語多読への適用可能性に関する基礎的検討2023

    • Author(s)
      加地修一朗, 新村正明, 香山瑞恵, 舘伸幸
    • Organizer
      2023年度 IEICE 信越支部大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Using lending history to recommend books for extensive reading2022

    • Author(s)
      SHUICHIRO KACHI, MASAAKI NIIMURA, MARK BRIERLEY
    • Organizer
      JALT PanSIG2022
    • Related Report
      2022 Research-status Report
  • [Presentation] Difficulty estimation method for extensive reading of general english books2022

    • Author(s)
      SAKAGUCHI RIHO, MASAAKI NIIMURA, MARK BRIERLEY
    • Organizer
      JALT PanSIG2022
    • Related Report
      2022 Research-status Report
  • [Presentation] Automatic question generation for an extensive reading placement test2022

    • Author(s)
      TOYOSHIMA KOTA, MASAAKI NIIMURA, MARK BRIERLEY
    • Organizer
      JALT PanSIG2022
    • Related Report
      2022 Research-status Report
  • [Presentation] The Potential of Machine Translation to Provide Online Extensive Reading2022

    • Author(s)
      MARK BRIERLEY
    • Organizer
      JALT2022 全国語学教育学会 第48回年次国際大会
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Extensive reading ABC: Agency, Books and Counting2022

    • Author(s)
      MARK BRIERLEY
    • Organizer
      JALT(全国語学教育学会)岐阜支部
    • Related Report
      2022 Research-status Report
    • Invited
  • [Presentation] Reading your way to better English2022

    • Author(s)
      MARK BRIERLEY
    • Organizer
      JALT(全国語学教育学会)豊橋支部
    • Related Report
      2022 Research-status Report
    • Invited
  • [Presentation] A Machine Learning Method for Estimating the Difficulty Level of Graded Readers2021

    • Author(s)
      Noda Yuki, Masaaki Niimura, Mark Brierley & Megumi HASEBE
    • Organizer
      Extensive Reading Around the World 2021
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Testing Extensive Reading2021

    • Author(s)
      Mark Brierley
    • Organizer
      Extensive Reading Around the World 2021
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 多読支援Webデータベースの開発2020

    • Author(s)
      中村涼真,新村正明, 増田武浩, Mark Brierley
    • Organizer
      Extensive Reading Summer Seminar 2020
    • Related Report
      2020 Research-status Report
  • [Presentation] Getting Students Reading: How and Why2020

    • Author(s)
      Mark Brierley
    • Organizer
      Yamagata JALT Presentation
    • Related Report
      2020 Research-status Report
  • [Presentation] Online reading e-books in the library2020

    • Author(s)
      Mark Brierley
    • Organizer
      Fukuoka JALT Presentation
    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi