Clustering Based Collaborative Learning Grouping for Knowledge Building

Jiaqi Hao, Weipo Yi, Meirui Ren, Chunyu Ai, Tianlong Qi, Longjiang Guo

Abstract: With the development of online learning, collaborative learning grouping has been paid more and more attention. In collaborative learning grouping, it is very important to develop new knowledge structures by building knowledge among collaborative learning partners, that is also the key process of knowledge building. For knowledge building in collaborative learning, this paper proposes a clustering grouping method called LGKB, which considers four factors: group size, topic willingness, learning time habit, and cognitive state. Compared with the existing grouping methods, LGKB increased the topic satisfaction and the study time similarity of members within the same group, and it enriched the knowledge structure of different group members. It results in the formation of collaborative learning groups in which students have higher interest and motivation to learn, and it is conducive to knowledge construction and the smooth progress of the collaborative learning process.