Semantic Topic-based Hybrid Learning Resource Recommendation
Lei Liu · 2015
Recommending learning resources to help readers understand any portion of the reading content where they have difficulty to understand is an useful and important task. Treating the whole unclear passage as the query and submit it to a search engine is unsuccessful since existing search engines were designed to accept small queries. In addition, as search engines usually transform the query and candidate resources into bags or vectors of words, the semantic topics underlying the content are totally overlooked. We believe that topics offer a better choice for truly understanding both the query and the candidate documents. In this paper, we propose a novel recommendation system for text content that facilitates the learning process by enabling search using as queries text passages of any length and retrieving a ranked list of resources (documents, videos, etc) that match the different topics covered within the selected passage. The recommended resources are ranked based on two criteria (a) how they match the different topics covered within the selected passage, and (b) the reading complexity level of the original text where the selected passage comes from. Our recommendation system has been built and being pilot from local universities and high schools, the user feedbacks from students who use our system in pilots for their courses suggest that our system is promising and effective. Beside this, we also provide a quantitative experimental evaluation, the results show that our proposed approach is promising and effective.