Ramesh, Arti, et al. "Weakly supervised models of aspect-sentiment for online course discussion forums." Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

This study introduces a weakly supervised joint model for aspect-sentiment analysis in MOOCs, addressing the challenge of limited labeled data. Using hinge-loss Markov random fields, the model captures dependencies between aspects and sentiment in forum posts. Tested on data from twelve online courses, each with about 10,000 posts, the model demonstrates improved accuracy in predicting both aspects and sentiments of posts compared to traditional methods.