Predicting Collaboration based on Students' Pauses in Online CSCL Conversations

As Computer Supported Collaborative Learning (CSCL) gains a broader usage as a viable alternative to traditional educational scenarios, the need for automated tools capable of evaluating active participation and collaboration among peers in online discussions increases. In this study, we validate a quantitative model of predicting involvement in CSCL chats based on student’s pauses throughout the timeline of the conversation. Starting from a corpus of 10 chat conversations, our proposed model explains 55% of the variance in terms of student participation and 42% in terms of collaboration, although relying on simple quantitative indices.This study is part of the RAGE project. The RAGE project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 644187. This publication reflects only the author's view. The European Commission is not responsible for any use that may be made of the information it contains