Download the full-sized PDF of Reciprocal Recommendation System and Formation of Learning Groups in Massive Open Online Courses (MOOCs)Download the full-sized PDF



Permanent link (DOI):


Export to: EndNote  |  Zotero  |  Mendeley


This file is in the following communities:

Graduate Studies and Research, Faculty of


This file is in the following collections:

Theses and Dissertations

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


Other title
Information Retrieval
Massive Open Online Courses
Reciprocal Recommendation
Type of item
Degree grantor
University of Alberta
Author or creator
Prabhakar, Sankalp
Supervisor and department
Zaiane, Osmar (Computing Science)
Examining committee member and department
Cutumisu, Maria (Educational Psychology)
Bulitko, Vadim (Computing Science)
Zaiane, Osmar (Computing Science)
Department of Computing Science

Date accepted
Graduation date
2017-06:Spring 2017
Master of Science
Degree level
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.
This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for the purpose of private, scholarly or scientific research. 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.
Citation for previous publication

File Details

Date Uploaded
Date Modified
Audit Status
Audits have not yet been run on this file.
File format: pdf (PDF/A)
Mime type: application/pdf
File size: 6320210
Last modified: 2017:06:13 12:12:18-06:00
Filename: Prabhakar_Sankalp_201611_MSc.pdf
Original checksum: bf60b5dbc71d7f6cb66767e1bb4afb43
Well formed: true
Valid: true
File title: thesis.pdf
Page count: 77
Activity of users you follow
User Activity Date