Enhancing collaborative learning in psychoeducation through social network analysis

Abstract

Abstract Social network opens up a practical new path for psychoeducation and, with the help of a multimedia mobile terminal’s network, text sentiment analysis for students’ mental health problem revelation and constructing corresponding psychoeducation model. Based on the above viewpoint, this paper proposes a semi-supervised learning method for sentiment analysis using graphs. Specifically, a graph-based semi-supervised learning classifier is constructed using the “Weibo-Weibo” relationship graph. At the same time, social network and text similarity relationships are combined. A link between annotated and unannotated texts was established, and an optimization algorithm was used to solve the model, revealing the psychological problems of students under the emotional texts of social networks, thus constructing a corresponding “four-in-one” mental health education model, which enhances the collaborative learning of students and the four major organizations in psychoeducation. The accuracy, accuracy, recall, and F1 value are outperformed by the model in this paper by 2.44%, 2.11%, 1.45%, and 2.34%, respectively. The eight questions designed around the three dimensions of collaborative learning situation, learning effectiveness, and four-in-one teaching model were highly rated by students. The four-in-one teaching model that utilizes social network sentiment analysis effectively enhances students’ collaborative learning and improves their ability to solve psychoeducation’s difficulties.