Abstract
Discussion forums are a valuable source of information in educational platforms such as Massive Open Online Courses (MOOCs), as users can exchange opinions or even help other students in an asynchronous way, contributing to the sustainability of MOOCs even with low interaction from the instructor. Therefore, the use of the forum messages to get insights about students’ performance in a course is interesting. This article presents an automatic grading approach that can be used to assess learners through their interactions in the forum. The approach is based on the combination of three dimensions: (1) the quality of the content of the interactions, (2) the impact of the interactions, and (3) the user’s activity in the forum. The evaluation of the approach compares the assessment by experts with the automatic assessment obtaining a high accuracy of 0.8068 and Normalized Root Mean Square Error (NRMSE) of 0.1799, which outperforms previous existing approaches. Future research work can try to improve the automatic grading by the training of the indicators of the approach depending on the MOOCs or the combination with text mining techniques.
Highlights
IntroductionPublisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations
Three experts on the topic of the Massive Open Online Courses (MOOCs) assisted in labeling 580 random messages (1% of the total number of messages in the entire dataset, each message was labeled by the three experts) at four different levels according to their quality, with level 1 being the lowest quality and level
The model presented in this paper evaluates the user based on the quality and impact of the messages he/she has posted and his/her activity within the forum, which is a more comprehensive and sustainable approach
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Massive Open Online Courses (MOOCs) are one of the new forms of digital education
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have