Use this URL to cite or link to this record in EThOS:
Title: Prediction of course completion based on participants' social engagement on a social-constructive MOOC platform
Author: Sunar, Ayse Saliha
ISNI:       0000 0004 7225 0850
Awarding Body: University of Southampton
Current Institution: University of Southampton
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
MOOCs offer world-widely accessible online content typically including videos, readings, quizzes along with social communication tools on a platform that enables participants to learn at their own pace. In 2016, over 58 million people join MOOCs. Far fewer people actually participate in MOOCs than originally sign up and then there is a steady attrition as courses progress. The observation of high attrition has prompted concerns among MOOC providers to mitigate their high attrition rates. Recent studies have been able to correlate social engagement of learners to course completion. Researchers use participants' digital traces to make sense of their engagement in a course and identify their needs to predict future patterns and to make interventions based on these patterns. The research reported here was conducted to further understand learners social engagement on a social-constructivist MOOC platform, the impact of engagement on course completion, and to predict learners' course completion. The findings of this research show that a commonly known social feature, follow, which is integrated into the Futurelearn MOOC platform has potential value in allowing tracking and analysing the behaviours of participants. The patterns of learners social engagement were modelled and a completion prediction model was developed. This model was successful at predicting those who might complete the course at a high or low success rate. The contributions of this research are that the behaviour chains could be the basis of a personalised recommender system, and the completion model based on social behaviour could contribute to wider prediction model based on a wider range of factors.
Supervisor: White, Susan Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available