Log Mining for Course Recommendation in Limited Information Scenarios

Recommender systems in educational contexts have proven effective to identify learning resources that fit the interests and needs of learners. Their usage has been of special interest in online self-learning scenarios to increase student retention and improve the learning experience. In current recommendation techniques, and in particular, in collaborative filtering recommender systems, the quality of the recommendation is largely based on the explicit or implicit information obtained about the learners. On free massive online learning platforms, however, the information available about learners may be limited and based mostly on logs from website analytics tools such as Google Analytics. In this paper, we address the challenge of recommending meaningful content with limited information from users by using rating estimation strategies from a log system. Our approach posits strategies to mine logs and generates effective ratings through the counting and temporal analysis of sessions. We evaluate different rating penalty strategies and compare the use of per-user and global metrics for rating estimation. The results show that using the average number of lessons viewed per-user is better than using global metrics with a p-value under 0.01 for 4 of our 5 hypotheses, showing statistical significance. Additionally, the results show that functions that penalize the rating to a lesser degree behave better and lead to a better recommendation. [For the full proceedings, see ED623995.]