Title: Language independent analysis and classification of discussion threads in Coursera MOOC forums
Abstract: In this work, we analyze the discussion threads from the forums of 60 Massive Open Online Courses (MOOCs) offered by Coursera and taught in 4 different languages. The types of interactions in such threads vary: there are discussions on close ended problems (e.g. solutions to assignments), open ended topics, course logistics, or just small talk among fellow students. We first study the evolution of the forum activities with respect to the normalized course duration. Then we investigate several language independent features to classify the discussion threads based on the types of the interactions among the users. We use default Coursera subforum categories (Study Groups, Assignments, Lectures, ...) to define the classes of interest and so the labels. We extract features related to structure, popularity, temporal dynamics of threads and diversity of the ids of the users. Text related features, word count aside, are avoided to apply the methods across discussion threads written in different languages and with various technical terminologies. Experiments show a classification performance with ROCAUC between 0.58 and 0.89, depending on the subforum class considered and with possibly noisy labels.
Publication Year: 2014
Publication Date: 2014-08-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 64
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot