Recognizing boundaries of online professional learning communities in an automated discourse analysis approach

Recognizing boundaries of online professional learning communities can help to provide teachers with a meaningful online learning environment that improves their training performance. This study proposed an automated discourse analysis approach for recognizing boundaries of the online learning communities, that combines both Topic Modelling approach (Latent Dirichlet Allocation) and Social Network Analysis. The study examined online discourse data of 1843 teachers participating in an online training program. The findings revealed that teachers mainly responded to others’ posts and the pattern of teachers’ response could be mainly divided into four types. The semantic network formed by discourse unit was high-density with low average network distance and high degree centrality, and the cohesion parameter of the semantic network was relatively stable during the whole process of online discourse. The findings of the study also can provide insights into creating online learning communities and teacher education.