Analyzing Social Networks and Learning Content on a Discussion Forum of an Introductory Programming MOOC in Higher Education

Massive Open Online Courses (MOOCs) are a well-established learning format in nonformal learning as well as in higher education that allows learners to benefit from self-paced learning. One of the main advantages of MOOCs is their scalability, which enables a high number of learners to enroll in a course due to a clear pre-defined course structure. Additionally, many MOOCs provide discussion forums to support learners during their learning process and provide room for discussion and feedback. These forums can give interesting insights into the interaction between course participants and educators and show which topics might cause problems. In this paper, we conduct an analysis of an introductory programming MOOC in higher education with 2,489 learners using different natural language processing (NLP) techniques. We classify the types of posts that are created and analyze the social network structure between the learners. Specifically, we use text classification techniques to identify different types of posts, such as questions, answers, and comments. Additionally, we analyze the network structure of the discussion subforums to gain insights into the interactions between learners. Our main findings are that there is a positive correlation between achievement in the course and active participation within the forum. The interaction between learners can strengthen the collaborative learning process of a MOOC. These results can be useful when establishing meaningful ways to communicate within MOOC forums, to provide a supportive learning experience.