Using Data Mining as a Strategy for Discovering User Roles in CSCL

Abstract

The purpose of this paper is to show how data mining may offer promise as a strategy for discovering learner's roles in CSCL. At present, there are many researchers who focus on analyzing learner roles based on collaborative learning activities. But most of them subjectively presume the diversity of learnerspsila roles in advance and then verify it based on the statistics of interaction data. In contrast, this paper adopts the data mining technology to explore learnerspsila roles in collaborative learning. Referring to the typical process of data mining, this paper proposes a framework of role analysis based on data mining which data preparation and learner discourse pattern mining are depicted. Furthermore, a case study is conducted to show the mining process and finding as well as discussion on the mining results.