Reciprocal Recommendation System and Formation of Learning Groups in Massive Open Online Courses (MOOCs)

• Author / Creator

  Prabhakar, Sankalp

• Online learning is an emerging education technology area with increasing demands. Massive open online courses (MOOCs) is one such platform where users with completely different backgrounds subscribe to various courses on offer. However, oftentimes these users are hesitant to approach other users for collaboration on certain tasks. In this paper, we propose a reciprocal recommender system that matches users who are mutually interested in, and likely to communicate with each other based on their profile attributes (age, location, gender, qualification, interests, grade etc.). We also present a ‘group formation’ strategy by using the particle swarm optimization based algorithm which would automatically generate dynamic learning groups. To form effective groups, we consider two important aspects: a) intra-group heterogeneity and b) inter-group homogeneity. Intra-group heterogeneity advocates the idea of diversity inside a particular group of users whereas inter-group homogeneity recommends that each group should be similar to the other. We test our algorithm on synthesized data sampled using the publicly avail- able MITx-Harvardx dataset. We measure the quality of generated groups based on a certain fitness measure, which is then compared against the fit- ness of groups obtained using the popular standard clustering algorithm like k-means. Evaluation of the recommender system is based on our own defined measures of precision, recall and normalized discounted cumulative gain. Experimental results show that our system performs better than the baseline models, therefore it makes a promising case for such a system to be implemented within an actual MOOC.

• Subjects / Keywords

  • Information Retrieval
  • Massive Open Online Courses
  • Reciprocal Recommendation

• Graduation date

  Spring 2017

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/R3DB7W286

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.