Sentiment evolution with interaction levels in blended learning environments: Using learning analytics and epistemic network analysis

Sentiment evolution is a key component of interactions in blended learning. Although have attracted considerable attention online learning contexts, there scant research on examining sentiment over different environments. Thus, this study, at interaction levels was investigated from the longitudinal data five stages 38 postgraduate students course. Specifically, text mining techniques were employed to mine sentiments interactions, and then epistemic network analysis (ENA) used uncover changes The findings suggested that negative moderately associated with several other such as joking, confused, neutral contexts. Particularly relation deep student might change insightful ones. In contrast, built social-emotion shows stronger connections joking-positive joking-negative than two levels. Most notably, co-occurrence reveal three periods process, namely initial, collision sublimation, stable periods. results study revealed students’ evolved positive confused/negative insightful.