Evaluation on Using Conversational Pedagogical Agents to Support Collaborative Learning in MOOCs

Massive Open Online Courses (MOOCs) introduce a way of transcending formal education by realizing technology-enhanced formats of learning and instruction and by granting access to an audience way beyond higher education. However, although MOOCs have been reported as an efficient and important educational tool, there is a number of issues and problems related to their educational impact. More specifically, there is an important number of dropouts during a course, little participation, and lack of students’ motivation and engagement overall. This paper updates the progress of the European project called “colMOOC” that aims to enhance the MOOCs experience by integrating collaborative settings based on conversational pedagogical agents to support both students and teachers during a MOOC course. Conversational pedagogical agents guide and support student dialogue using natural language both in individual and collaborative settings. Integrating this type of conversational agents into MOOCs to trigger peer interaction in discussion groups can considerably increase the engagement and the commitment of online students and, consequently, reduce MOOCs dropout rate. The paper reports on the first evaluation experience of incorporating synchronous collaborative activities mediated by conversational pedagogical agents into a real MOOC with a massive international participation. Evaluation results are statistically described in terms of participation, performance and satisfaction. The research reported in this paper is currently undertaken within the project colMOOC funded by the European Commission.