Understanding Learners´ Interaction Patterns through Analyzing Context of Questions in Discussion Transcripts

In CSCL research, the collaborative process is of central importance. Thus, this paper aims to unveil learners´ interaction patterns through analyzing context of questions in discussion transcript. Based on assumptions on data source and users´ operating process of analyzing questions´ context, several design principles have been identified. Guided by these principles, a technical solution is presented to implement a tool for analyzing context of questions. By incorporating text classification and information visualization technologies, the tool supports content and structure analysis of discussion transcripts to generate visual patterns in a form of 5W1H context of questioning. In this way, the tool enables users to understand interaction patterns in an intuitive and friendly manner. A case study is also conducted to validate the effectiveness of the tool.