A sentiment analysis approach for supporting blended learning process

E-Learning is one of the most widely used training approaches in recent years. Numerous universities and training institutions adopt this approach to deliver courses or support the students in their training process. In particular, the blended E-Learning is a useful approach for supporting students and better understanding their learning issues. The possibility of using collaborative tools and interacting with other students allows the student to share doubts on certain topics. The teacher often remains outside of this dynamic and does not understand the learning problems that characterize the class. A possible solution, which ensures the privacy of communication between students, is the Sentiment Analysis. The computational study of opinions, feelings and emotions expressed in a text often relates to the identification of agreement or disagreement with statements, contained in comments that convey positive or negative feelings. In this paper, we investigate the adoption of a probabilistic approach based on the Latent Dirichlet Allocation (LDA) as Sentiment Grabber. Through this approach, for a set of documents belonging to a same knowledge domain, a graph, the Mixed Graph of Terms, can be automatically extracted. The paper shows how this graph contains a set of weighted word pairs, which are discriminative for sentiment classification. In this way, the system can detect the feeling of students on some topics and teacher can better tune his/her teaching approach. In fact, the proposed method has been tested in real cases with effective and satisfactory results.