Conflict recognition in CSCL sessions through the identification of cycles in conversational graphs

Abstract

Conflicts play an important role to improve group learning effectiveness; they can be decreased, increased, or ignored. Given the sequence of messages of a collaborative group, we are interested in recognizing conflicts (detecting whether a conflict exists or not). This is not an easy task because of different types of natural language ambiguities. A conversation can be represented as a conversation graph; i.e., a direct multidigraph where the nodes are users, and an edge means a message. The approach proposed in this paper focuses on the emotional interactions of group members. Hence, to detect conflicts it analyzes emotions involved in the cycles of the graph. This strategy has the advantages of considering the sentiment of a sequence of messages to take a better decision and analyzing interactions with two or more participants. The proposed approach has been tested in collaborative learning tasks, achieving an F1 score of 92.6%, and a 90.1% recall score for conflicting situations. This approach can help teachers and students to improve the learning process.