Rossi, Lorenzo A., and Omprakash Gnawali. "Language independent analysis and classification of discussion threads in Coursera MOOC forums." Proceedings of the 2014 IEEE 15th international conference on information reuse and integration (IEEE IRI 2014). IEEE, 2014.

This study analyzes discussion threads from 60 MOOCs on Coursera, taught in four different languages, focusing on various interaction types such as problem-solving, course logistics, and casual conversation. The research examines how forum activities evolve over the course duration and classifies threads based on interaction types using language-independent features. Utilizing Coursera's subforum categories (e.g., Study Groups, Assignments), the study extracts structural, popularity, temporal, and user diversity features, avoiding text-related metrics to maintain cross-language applicability. Classification experiments achieved a ROCAUC performance ranging from 0.58 to 0.89, indicating variability depending on the subforum class.