Evaluating On-Line Courses via Reviews Mining

Abstract

Because the participants are not limited by age-, gender-, race-, or geography-related barriers, recently, massive open online courses (MOOC) have witnessed remarkable growth in number of online self-learners, courses providers and online platforms. MOOC learners usually share some learning experiences and release millions of course-related comments in discussion forum. On the one hand, these comments could reflect the learners’ attitudes toward the online courses. On the other hand, semantic knowledge hidden in these comments would assist other learners to choose the appropriate courses and help instructors to improve their courses’ attraction. Recently, few research works focus on evaluating the courses through reviews mining. Thus, this paper constructs a curriculum evaluation system based on MOOC reviews, which quantifies the curriculum from different topics. Firstly, we employ latent dirichlet allocation (LDA) to mine the reviews generated by students, and obtain a topic-word distribution matrix and a comment-topic distribution matrix which can describe the topics of the course comments. Next, the emotion values of the comments in each topic are calculated by the auto-encoder and Bi-LSTM text classification model. We utilize the emotions and the quantified scores of the courses on different topics to establish a comprehensive curriculum evaluation system. The experimental results show that there are five main indicators abstracted from students’ reviews, which are instructor, course content, course assessment, MOOC platform, and hot courses. Moreover, comment texts of each course under different evaluation indicators are objectively and accurately converted into numerical marks, which can provide the students and educators with reliable references.