Publication Type : Conference Paper
Thematic Areas : Amrita e-Learning Research Lab
Publisher : Proceedings - IEEE 8th International Conference on Technology for Education, T4E 2016, Institute of Electrical and Electronics Engineers Inc.,
Source : Proceedings - IEEE 8th International Conference on Technology for Education, T4E 2016, Institute of Electrical and Electronics Engineers Inc., p.194-199 (2017)
ISBN : 9781509061150
Keywords : Apriori algorithms, Association analysis, Current performance, E-learning, Education, Education computing, Experimental analysis, Learning Analytics, Massive open online course, MOOCS, Real-Time Feedback, risk assessment, Risk management, Students
Campus : Amritapuri
School : School of Engineering
Center : E-Learning
Department : E-Learning
Year : 2017
Abstract : MOOCs (Massive Open Online Courses) have revolutionized the way we learn. But a major challenge faced by MOOCs is the high dropout rates among students at various stages of the course. It is important to identify the students at risk in terms of those who are likely to drop out at some stage of the course and those who might not meet the required passing criteria. In this paper, a model is proposed to identify learners who are at risk in an online course using association analysis which is done with dataset of students who have taken the course previously. Identifying such learners who are at risk and providing them real time feedback would help the students to be more aware of their current performance and to improve upon it. Several experiments were conducted to test the performance of the proposed work and the results show that the proposed model identifies 90% of the learners who are at risk. Out of 4,74,977 students, 4,32,502 were identified as at risk students based on the experimental analysis.
Cite this Research Publication : M. Srilekshmi, Sindhumol, S., Chatterjee, S., Kamal Bijlani, Kinshuk,, and S., M., “Learning Analytics to Identify Students At-risk in MOOCs”, in Proceedings - IEEE 8th International Conference on Technology for Education, T4E 2016, 2017, pp. 194-199.