Evaluation of Automatic Coding for Collaborative Learning Process Based on Multi-Dimensional Coding Scheme

• Published in: Journal of Learning Analytics Vol. 2; pp. 11 - 22
• Main Authors: Ando, Kimihiko, Shibata, Chihiro, Zhan, Jin, Inaba, Taketoshi
• Format: Journal Article
• Language: Japanese
• Published: Japanese Society for Learning Analytics 2018; 特定非営利活動法人 学習分析学会
• Subjects: Coding Scheme; Collaborative Process; Computer Supported Collaborative Learning; Deep Learning; コンピュータ支援協調学習; コーディングスキーム; 協調プロセス; 深層学習
• ISSN: 2436-6862
• DOI: 10.51034/jasla.2.0_11

In computer-supported collaborative learning research, it may be a significantly important task to figure out guidelines for carrying out an appropriate scaffolding by extracting indicators for distinguishing groups with poor progress in collaborative process upon analyzing the mechanism of interactive activation. And for this collaborative process analysis, coding and statistical analysis are often adopted as a method. But as far as our project is concerned, we are trying to automate this huge laborious coding work with deep learning technology. In our previous research, supervised data was prepared for deep learning based on a coding scheme consisting of 16 labels according to speech acts. In this paper, with a multi- dimensional coding scheme with five dimensions newly designed aiming at analyzing collaborative learning process more comprehensively and multilaterally, an automatic coding is performed by deep learning methods and its accuracy is verified. In addition, we apply our methods to predict another dataset for verification and investigate the correlation between the multidimensional coding labels and the assessments given by professionals manually.