author={S. Singh and S. P. Lal},
booktitle={2013 IEEE Conference on e-Learning, e-Management and e-Services},
title={Educational courseware evaluation using Machine Learning techniques},
keywords={courseware;human computer interaction; Prediction algorithms; attribute ranking;e-learning;machine learning},

Please cite as:

S. Singh and S. P. Lal, "Educational courseware evaluation using Machine Learning techniques," in Proceedings of the 2013 IEEE Conference on e-Learning, e-Management and e-Services , Kuching, 2013, pp. 73-78.

doi: 10.1109/IC3e.2013.6735969

With the introduction of massive open online courses (MOOCs) and other web-based learning management systems (LMS), there is a greater need to develop methods for exploring the unique types of data that come from the educational context. This paper highlights the advantage of using Machine Learning (ML) as an e-planning tool to enhance learning and improve courseware development. Researchers generally consider student evaluation survey on courses to be highly reliable and at least moderately valid on courseware evaluation. However, low response rate, retaliation, grades and comparison with past instructors sometimes affects the reliability of the result. ML algorithms has been deployed in this paper to intelligently examine the interaction log data from the LMS to obtain a predictive map that permits mapping the online interaction behaviour of students with their course outcome. These predictive relationships are then investigated and ranked using various ML algorithms to evaluate and validate the various learning tools and activities, and their effectiveness within the course.

keywords: {interaction data;machine learning technique; Least squares approximations;Prediction algorithms;Artificial Intelligence;attribute ranking;e-learning;}

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6735969&isnumber=6735951