Sentiment analysis in MOOCs: A case study

Forum messages in MOOCs (Massive Open Online Courses) are the most important source of information about the social interactions happening in these courses. Forum messages can be analyzed to detect patterns and learners' behaviors. Particularly, sentiment analysis (e.g., classification in positive and negative messages) can be used as a first step for identifying complex emotions, such as excitement, frustration or boredom. The aim of this work is to compare different machine learning algorithms for sentiment analysis, using a real case study to check how the results can provide information about learners' emotions or patterns in the MOOC. Both supervised and unsupervised (lexicon-based) algorithms were used for the sentiment analysis. The best approaches found were Random Forest and one lexicon based method, which used dictionaries of words. The analysis of the case study also showed an evolution of the positivity over time with the best moment at the beginning of the course and the worst near the deadlines of peer-review assessments.

I. Introduction

In MOOCs (Massive Open Online Courses), learners can establish social interactions with other users to ask or answer questions, with no or little support of teachers. Although there are different ways of communication, including social networks, like Facebook or Twitter, the bulk of the social interactions usually occur in the course forum [1]. In a MOOC, the number of enrolled users can be huge (it is possible to find courses with up to 100,000 learners) and, although most of them enroll just to explore [2], the total number of forum messages can be very large, and it is not feasible to read and analyze all of them individually.