Programming Learning Support System Exposing Learners' Experiences as Feedback

• Project/Area Number: 17K12804
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Learning support system
• Research Institution: Kyushu University
• Principal Investigator: Taniguchi Yuta 九州大学, 情報基盤研究開発センター, 助教 (20747125)
• Project Period (FY): 2017-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000); Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2017: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: プログラミング学習 / 学習過程 / エラー解決 / ソースコード / 編集 / 学習支援システム / 系列モデリング / 学習行動 / 早期予測 / 共起関係の分析 / エラーの特徴付け / データ構造化 / エラーの普遍性 / e-ラーニング / 学習支援 / フィードバック

Outline of Final Research Achievements

In this study, we conducted research and development to support teachers and learners by automatically understanding the situation of learners in programming exercise classes through analysis of their learning activity log data. Specifically, we analyzed compiler error messages and a series of learning activity sequences, and developed a method to predict whether learners can solve errors themselves or not. We found that the errors encountered by learners are almost always unique and need to be taken care of individually. We also developed a prediction method for early prediction with a certain degree of accuracy.

Academic Significance and Societal Importance of the Research Achievements

本研究の意義は、昨今ますます重要視されているプログラミング学習に対し、自動的な学習支援のための学習環境の開発と支援技術開発を行ったことである。また、ラーニングアナリティクス分野において、学習の過程を詳細に記録可能なプログラミング演習を題材に、電子教科書システムとプログラミング学習システムという異種システムの双方から得られる、マルチモーダルなログデータを分析するための手法を開発して、多様な学習活動ログを組み合わせることの有用性を示した。

Research Products

• [Presentation] 構成的学習環境 (2020)
  • Author(s): 谷口雄太, 峰松翼, 島田敦士
  • Organizer: 情報処理学会 第31回CLE研究発表会
• [Presentation] Collecting and Integrating Multimodal Data from a Programming Exercise Environment (2020)
  • Author(s): Yuta Taniguchi and Atsushi Shimada
  • Organizer: Workshop on Integrating Multi-Channel Learning Data to Model Complex Learning Processes at the LAK 2020 Conference
  • Int'l Joint Research
• [Presentation] Investigating Error Resolution Processes in C Programming Exercise Courses (2019)
  • Author(s): Yuta Taniguchi, Atsushi Shimada, Shin'ichi Konomi
  • Organizer: The 12th International Conference on Educational Data Mining (EDM 2019)
  • Int'l Joint Research
• [Presentation] How are Students Struggling in Programming? Understanding Learning Processes from Multiple Learning Logs (2018)
  • Author(s): Yuta Taniguchi, Fumiya Okubo, Atsushi Shimada, Shin'ichi Konomi
  • Organizer: The 11th International Conference on Educational Data Mining (EDM 2018)
  • Int'l Joint Research