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

Computerized Adaptive Testing Method using Integer Programming to Minimize Item Exposure

Research Project

Project/Area Number 18K18166
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 62030:Learning support system-related
Research InstitutionThe National Center for University Entrance Examinations

Principal Investigator

Yoshimitsu Miyazawa  独立行政法人大学入試センター, 研究開発部, 助教 (70726166)

Project Period (FY) 2018-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Keywords適応型テスト / eテスティング / 項目反応理論 / 教育工学 / Computer Based Testing / 数理計画問題 / テスト構成 / e-テスティング / Computer Based testing / 等質適応型テスト / CBT / 複数等質テスト
Outline of Final Research Achievements

We propose Computerized adaptive testing(CAT) item selection using integer programming. It can select a different item while maintaining equal accuracy, even for an examinee with the same ability. The approach of the proposed method is described as presented below. 1) A group that satisfies test constraints as Fisher information is assembled using integer programming for minimizing item exposure. 2) An item that has the highest information is selected from the group. The proposed method uses integer programming for minimizing item exposure and satisfying upper and lower bounds of information. Accordingly, a different item set can be selected, even for an examinee with equal ability. Moreover, the improved diversity of item selection is expected to encourage thorough use of items in an item pool and to mitigate deviation in exposure.

Academic Significance and Societal Importance of the Research Achievements

従来の適応型テストでは,同一の受検者が複数回受験した場合には,同一の項目群が出題される傾向があり,実際に適応型テストを導入しているテスト事業者の重要な問題になっている。また,特定の項目群が過度に受検者に暴露されてしまう傾向があるため,項目内容の暴露につながり,テストの信頼性の低下要因となりうる。さらに,測定精度の等質化が実現されておらず,テストの長さや測定精度について受検者間で大きな差が生じるという問題がある。本研究では,これらの課題を解消し,適応型テストの実用化に寄与しており,学術的にも社会的にも意義がある。

Report

(4 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (8 results)

All 2020 2019 2018

All Journal Article (1 results) Presentation (7 results) (of which Int'l Joint Research: 1 results,  Invited: 1 results)

  • [Journal Article] Computerized Adaptive Testing Method Using Integer Programming to Minimize Item Exposure2020

    • Author(s)
      Yoshimitsu Miyazawa, Maomi Ueno
    • Journal Title

      Advances in Artificial Intelligence: Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence

      Volume: 1128 Pages: 105-113

    • DOI

      10.1007/978-3-030-39878-1_10

    • NAID

      130007658840

    • ISBN
      9783030398774, 9783030398781
    • Related Report
      2020 Annual Research Report
  • [Presentation] 複数等質テスト構成技法を用いた適応型テストの項目選択手法の提案2020

    • Author(s)
      宮澤 芳光, 植野 真臣
    • Organizer
      日本行動計量学会
    • Related Report
      2020 Annual Research Report
  • [Presentation] Uniform adaptive testing using maximum clique algorithm2020

    • Author(s)
      宮澤 芳光, 植野 真臣
    • Organizer
      情報処理学会
    • Related Report
      2020 Annual Research Report
    • Invited
  • [Presentation] Uniform adaptive testing using maximum clique algorithm2019

    • Author(s)
      Maomi Ueno, Yoshimitsu Miyazawa
    • Organizer
      Artificial Intelligence in Education
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] 最適化問題を用いた等質適応型テスト2019

    • Author(s)
      宮澤芳光,植野真臣
    • Organizer
      日本行動計量学会
    • Related Report
      2019 Research-status Report
  • [Presentation] Computerized Adaptive Testing Method using Integer Programming to Minimize Item Exposure2019

    • Author(s)
      Yoshimitsu Miyazawa, Maomi Ueno
    • Organizer
      人工知能学会
    • Related Report
      2019 Research-status Report
  • [Presentation] 項目暴露率を考慮した等質適応型テスト2019

    • Author(s)
      宮澤芳光,植野真臣
    • Organizer
      日本テスト学会
    • Related Report
      2019 Research-status Report
  • [Presentation] 整数計画問題を用いた等質適応型テストの提案2018

    • Author(s)
      宮澤 芳光,植野 真臣
    • Organizer
      日本テスト学会
    • Related Report
      2018 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi