Back to search

The colMOOC: Integrating Conversational Agents and Learning Analytics in MOOCs

588438-EPP-1-2017-1-EL-EPPKA2-KA2017Knowledge Alliances for higher educationfinalized
Countries: EL|DK|DE|ES|CY · Grant: €999,673

Project summary

Higher Education Massive Open Online Courses (MOOCs) introduce a way of transcending formal higher education by realizing technology-enhanced formats of learning and instruction and by granting access to an audience way beyond students enrolled in any one Higher Education Institution. The potential for European HEIs to scale up and reach an international audience of diverse backgrounds has not been realized yet. Although MOOCs have been reported as an efficient and important educational tool, there is a number of issues and problems related to the educational aspect. More specifically, there is an important number of drop outs during a course, little participation, and lack of students’ motivation and engagement overall. This may be due to one-size-fits-all instructional approaches and very limited commitment to student-student and teacher-student collaboration.Our project aims to enhance the MOOCs experience by integrating: • Collaborative settings based on Conversational Agents (CA) both in synchronous and asynchronous collaboration conditions• Screening methods based on Learning Analytics (LA) to support both students and teachers during a MOOC course• Reinforce European leadership by forming recommendations and policy guidelinesConversational pedagogical agents 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 conversational agents into MOOCs to trigger peer interaction in discussion groups is expected to considerably increase the engagement and the commitment of online students (and, consequently, reduce MOOCs dropout rate). Moreover, this project will use learning analytics techniques, as a method to support teachers’ orchestration and students’ learning during MOOCs by evaluating students' interaction and participation.

Objectives

O1. Develop new learning and teaching methods for MOOCs building on novel technologies in collaborative learning like conversational agents.O2. Promote innovative solutions to current and future challenges and for sustainable impact on Europe’s education and training systems. O3. Demonstrate and validate the built capacity for innovative teaching and learning methods. O4. Spread the best practice pilots built in the project to all participating universities.

Background

The colMOOC project produced a conversational agent component that can be embedded in MOOCs chat rooms and pose domain relevant questions to peers facilitating productive forms of dialogue, and a relevant learning analytics component, providing visualized feedback relevant to these activities. The colMOOC project has developed four pilot MOOCs and administered 12 ‘trials’ (experimental activities) engaging MOOC learners in interactive social forms of learning facilitated by CA/LA components.

Final report summary

<< Background >> The colMOOC project produced a conversational agent component that can be embedded in MOOCs chat rooms and pose domain relevant questions to peers facilitating productive forms of dialogue, and a relevant learning analytics component, providing visualized feedback relevant to these activities. The colMOOC project has developed four pilot MOOCs and administered 12 ‘trials’ (experimental activities) engaging MOOC learners in interactive social forms of learning facilitated by CA/LA components. << Objectives >> O1. Develop new learning and teaching methods for MOOCs building on novel technologies in collaborative learning like conversational agents.O2. Promote innovative solutions to current and future challenges and for sustainable impact on Europe’s education and training systems. O3. Demonstrate and validate the built capacity for innovative teaching and learning methods. O4. Spread the best practice pilots built in the project to all participating universities. << Implementation >> The colMOOC project organized implementation in 8 WorkPackages as follows: •WP1: Educational approach construction and framework •WP2: Conversational agent component •WP3: Learning analytics component•WP4: System Integration•WP5: Courses preparation, trials and evaluation •WP6: Policy recommendations and Community of Practice •WP7: Dissemination, Exploitation & Impact•WP8: Project Management Two amendments of the initial project workplan took place during implementation. << Results >> R1.1: CA/LA components and related pedagogical methods developed and their impact explored.R2.1: The colMOOC platform can be flexibly embedded to different MOOC platform R3.1: Overall 12 trials (research activities) utilizing 10 MOOC “editions” of the four pilot MOOCs.R4.x: Info days and workshop, Project website, Virtual Community of Practice, Policy recommendation list, Scientific publications, Dissemination actions, Exploitation and sustainability plan

Project partners (9)