Wu, Jiun-Yu, Yi-Cheng Hsiao, and Mei-Wen Nian. "Using supervised machine learning on large-scale online forums to classify course-related Facebook messages in predicting learning achievement within the personal learning environment." Interactive Learning Environments 28.1 (2020): 65-80.

This paper explores the use of supervised Machine Learning (ML) for text classification to predict students’ final grades in a hybrid Advanced Statistics course. The study built three classification models using 76,936 posts from two large online forums, which were then applied to classify messages in a private Facebook group into statistics-related and non-statistics-related posts. Three ML algorithms were compared for their classification effectiveness and congruency with human coding. The study found that students with more posts classified as statistics-related by at least two ML algorithms had higher final grades, while students who failed the course had significantly fewer such posts. The results suggest that ML can identify students needing support in a personal learning environment and ensure quality control of large-scale educational data.