Temporal Affiliation and Emotion in MOOC Forums: A Discourse-Centered Learning Analytics Perspective

Abstract

Online Learning Discourse now turns on the ability to balance performance with evidence quality, resource limits, and transfer across settings. The present synthesis investigates analyzing how social language changes over time and what those changes can and cannot reveal about learning. The evidence base combines 1 focal paper with 12 independently retrieved publications reviewed against traceable publication metadata. The analysis is organized around discourse markers, temporal modeling, participation bias, instructional interpretation, and privacy. Instead of assuming that headline results as if they shared one denominator, the review compares units of analysis, methodological commitments, and evidence limits. Across the literature, the recurring conclusion is that advances in online learning discourse become credible when behavior, measurement, and decision context are evaluated together and when uncertainty about selection effects is reported explicitly. The framework consequently connects method selection to application risk, identifies recurring threats to external validity, and proposes a research agenda centered on comparable baselines, sensitivity analysis, and retained provenance.