Identification of latent skill dynamics and visualization of learning effect by educational data mining

2023 Fiscal Year Final Research Report

• Project/Area Number: 19H01728
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 09070:Educational technology-related
• Research Institution: Kisarazu National College of Technology
• Principal Investigator: Oeda Shinichi 木更津工業高等専門学校, 情報工学科, 教授 (80390417)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: 教育データマイニング / 潜在的スキル構造 / プログラミング教育 / Student Modeling / Skill Modeling / Q-matrix / 学習効果の可視化 / 学習中のログデータ

Outline of Final Research Achievements

In the fields of business and healthcare, research on data mining is thriving. However, in the field of education, despite the accumulation of big data, such as vast amounts of test results and log data, data mining methods that use machine learning to extract latent skill structures have not yet been established. Therefore, this study aims to develop data mining techniques that automatically extract the latent skill structures necessary for acquiring knowledge from test results and learning process log data. Specifically, we propose a method to analyze log data and source code obtained from programming classes to identify students who are not keeping up with the coursework. Additionally, we extend the commonly used Knowledge Tracing model to better fit our analysis.

Free Research Field

知能情報学

Academic Significance and Societal Importance of the Research Achievements

近年，実用的なe-Learningシステムが教育現場で活用されている．e-Learningシステムは，学生の試験結果や学習過程のログデータを保存することが容易であるため，Educational Data Miningでは，これらの膨大な教育関連のデータから，いかにして意味のある情報を抜き出すかが研究の焦点となっている． 我々は調査対象をプログラミング教育とした．プログラミング言語は修得が早い学習者，遅い学習者が顕著に現れる．なぜ，このような事象が生じるのか解明できれば，IT技術者の早期育成の一助となり，日本国内のIT人材不足を解消できると考えている．