Classifying MOOC forum posts using corpora semantic similarities: a study on transferability across different courses

Abstract

Information overload in MOOC discussion forums is a major problem that hinders the effectiveness of learner facilitation by the course staff. To address this issue, supervised classification models have been studied and developed in order to assist course facilitators in detecting forum discussions that seek for their intervention. A key issue studied by the literature refers to the transferability of these models to domains other than the domain in which they were initially trained. Typically these models employ domain-dependent features, and therefore they fail to transfer to other subject matters. In this study, we propose and evaluate an alternative way of building supervised models in this context, by using the semantic similarities of the forum transcripts with the dynamically created corpora from the MOOC environment as training features. Specifically, in this study, we analyze the case of two MOOCs, in which the models that we built are classifying forum discussions into three categories, course logistics, content-related and no action required. Furthermore, we evaluate the transferability of the derived models and interpret which features can be effectively transferred to other unseen courses. The findings of this study reveal the main benefits and trade-offs of the proposed approach and provide MOOC developers with insights about the main issues that inhibit the transferability of these models.