2017/09/28 by Iacopo Vagliano, Vagliano, Iacopo, Diego Monti +5
Computer Science · #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Recommender Systems and Techniques #Sentiment Analysis and Opinion Mining #Topic Modeling #Web Data Mining and Analysis
paper · pdf · doi:10.48550/arxiv.1709.09973
openalex publication_date 2017/09/28 · openalex created_date 2022/09/03 · openalex updated_date 2026/07/28
Nowadays, most recommender systems exploit user-provided ratings to infer\ntheir preferences. However, the growing popularity of social and e-commerce\nwebsites has encouraged users to also share comments and opinions through\ntextual reviews. In this paper, we introduce a new recommendation approach\nwhich exploits the semantic annotation of user reviews to extract useful and\nnon-trivial information about the items to recommend. It also relies on the\nknowledge freely available in the Web of Data, notably in DBpedia and Wikidata,\nto discover other resources connected with the annotated entities. We evaluated\nour approach in three domains, using both DBpedia and Wikidata. The results\nshowed that our solution provides a better ranking than another recommendation\nmethod based on the Web of Data, while it improves in novelty with respect to\ntraditional techniques based on ratings. Additionally, our method achieved a\nbetter performance with Wikidata than DBpedia.\n