Conversational Agents in Support for Collaborative Learning in MOOCs: An Analytical Review

Abstract

Massive Open Online Courses (MOOCs) arose as a way of transcending formal higher education by realizing technology-enhanced formats of learning and instruction and by granting access to a wide audience way beyond students enrolled in any one Higher Education Institution. However, while MOOCs have been reported as an efficient and important educational tool, yet there is a number of issues and problems related to their educational impact. More specifically, there is an important number of drop outs during a course, little participation, and lack of students’ motivation and engagement overall. To overcome these limitations, Conversational pedagogical agents have arisen to guide and support student dialogue using natural language both in individual and collaborative settings. Conversational agents have been produced to meet a wide variety of applications and studies exploring the usage of such agents have led to positive results. Integrating this type of artificial agents into MOOCs is expected to trigger productive peer interaction in discussion groups. In this paper, we present a state-of-the-art study of the use of conversational agents to support collaborative learning in the context of MOOCs. The ultimate goal of this study is to analyze the potential of conversational agents to considerably increase the engagement and the commitment of MOOC students, reducing consequently, the overall MOOCs dropout rate. The research reported in this paper is currently undertaken within the research project colMOOC funded by the European Commission.