Context-Based Rating Prediction using Collaborative Filtering and Linked Open Data
Vineet Kumar Sejwal, Muhammad Abulaish · 2019
Linked Open Data (LOD) consists of various knowledgebases, such as DBpedia, Yago, and Freebase, and uses structured data as features to conceptualize a domain of interest. During last few years, many researchers have shown how LOD can be utilized in various applications, including recommender systems that are used to map items and users generally on the basis of interest and similarity parameters. However, contextual features play an important role to improve the effectiveness of the recommender systems. In this paper, we propose a contextual feature-based rating prediction and recommendation technique using item-based collaborative filtering and LOD. To this end, we have generated a RDF graph representing items and their contextual features, which help to determine context-based similar items for recommendation using graph matching techniques. In order to extract contextual features for item profiling, we have used LOD and two famous movie data sources, Rotten Tomatoes and IMDB. We also propose a rating prediction model to predict the rating of the non-rated items with the help of the RDF graph and item-based collaborative filtering. The proposed approach is evaluated using mean absolute error and root mean square error, and performs significantly better in comparison to some of the standard baseline methods.