Investigating learners' behaviors and discourse content in MOOC course reviews.

In MOOCs, course reviews serve as a new interactive tool that has not yet been sufficiently exploited. Therefore, this study investigated learners' explicit behaviors and implicit discourse content derived from reviews by using a mixed approach of text mining and statistical analysis. We proposed an improved topic model called Behavior–Emotion Topic Model (BETM) to detect reviews' semantic content between two achievement groups (completers and non-completers). Then we performed statistical analysis to investigate differences in the two groups' discourse behaviors and content. Results showed significant differences in discourse behaviors and focused topics between completers and non-completers. Specifically, posting reviews was a significant behavior for completers, while replying and giving peers' reviews "thumps up" were significant behaviors for non-completers. Furthermore, completers tended to express appreciation of course-related content by posting reviews and, afterward, showing certificates, whereas non-completers tended to hold negative attitudes toward the platform construction's technical issues by replying. Finally, we conducted an evolutionary analysis to explore the dynamics of learners' focused content throughout the course over 3 years; this can provide instructors new insights for the development of online course, thus meeting future learners' needs by adjusting the teaching process. • Significant differences are shown in discourse behaviors and focused topics between completers and non-completers. • Completers are more likely to express appreciation of course-related content by posting. • Non-completers tend to hold negative attitudes toward the technical issues of platform construction by replying. • Learners' behaviors and opinions toward focused topics evolve toward a stable state throughout the course. [ABSTRACT FROM AUTHOR]