Content Recommendation through Semantic Annotation of User Reviews and Linked Data - An Extended Technical Report

TL;DR

This paper presents a novel recommendation system that leverages semantic annotation of user reviews and linked data from DBpedia and Wikidata to improve ranking and novelty over traditional rating-based methods.

Contribution

It introduces a new approach combining semantic annotation of reviews with linked data to enhance recommendation quality and novelty, evaluated across three domains.

Findings

Outperforms Web of Data-based recommendation methods in ranking.

Improves novelty compared to traditional rating-based techniques.

Achieves better performance with Wikidata than with DBpedia.

Abstract

Nowadays, most recommender systems exploit user-provided ratings to infer their preferences. However, the growing popularity of social and e-commerce websites has encouraged users to also share comments and opinions through textual reviews. In this paper, we introduce a new recommendation approach which exploits the semantic annotation of user reviews to extract useful and non-trivial information about the items to recommend. It also relies on the knowledge freely available in the Web of Data, notably in DBpedia and Wikidata, to discover other resources connected with the annotated entities. We evaluated our approach in three domains, using both DBpedia and Wikidata. The results showed that our solution provides a better ranking than another recommendation method based on the Web of Data, while it improves in novelty with respect to traditional techniques based on ratings. Additionally, our method achieved a better performance with Wikidata than DBpedia.