A course hybrid recommender system for limited information scenarios

Recommender systems in educational contexts have proven to be effective in identifying 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 this article,
we present the design of a hybrid course recommendation system for an online learning platform. The
proposed hybrid system articulates the recommendation carried out by collaborative and content-based
filter strategies. For the collaborative filtering recommender, we address the challenge of recommending
meaningful content with limited information from users by using rating estimation strategies from a log
system (Google Analytics). 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 metrics for rating estimation. For the content-based recommender, we
compare different text embeddings that range from well-known topic models (LSA and LDA) to more
recent multilingual contextual embeddings pre-trained on large-scale unlabelled corpora. The results
show that the best model in terms of P@5 was the Collaborative filtering recommendation model with
a value of 0:4, i.e., two out of five courses recommended could be of the user’s interest. This result is
satisfactory considering that our models were trained from ratings inferred from implicit user data. The
content-based strategies did not yield significant results, however, these strategies help to mitigate the
cold start problem and validate the use of a combined hybrid strategy.