MindReader: Recommendation over Knowledge Graph Entities with Explicit User Ratings
This work addresses a data limitation in knowledge graph-based recommendation systems, offering a new dataset and insights that could enhance recommendations, particularly for cold-start scenarios, though it is incremental as it builds on existing models.
The authors tackled the lack of explicit user ratings for non-item knowledge graph entities in recommendation systems by introducing the MindReader dataset, which includes over 102,000 ratings from 1,174 users on both items and entities, and demonstrated that incorporating these ratings improves recommendation quality in various models, with some models achieving comparable performance using only non-item ratings.
Knowledge Graphs (KGs) have been integrated in several models of recommendation to augment the informational value of an item by means of its related entities in the graph. Yet, existing datasets only provide explicit ratings on items and no information is provided about user opinions of other (non-recommendable) entities. To overcome this limitation, we introduce a new dataset, called the MindReader, providing explicit user ratings both for items and for KG entities. In this first version, the MindReader dataset provides more than 102 thousands explicit ratings collected from 1,174 real users on both items and entities from a KG in the movie domain. This dataset has been collected through an online interview application that we also release open source. As a demonstration of the importance of this new dataset, we present a comparative study of the effect of the inclusion of ratings on non-item KG entities in a variety of state-of-the-art recommendation models. In particular, we show that most models, whether designed specifically for graph data or not, see improvements in recommendation quality when trained on explicit non-item ratings. Moreover, for some models, we show that non-item ratings can effectively replace item ratings without loss of recommendation quality. This finding, thanks also to an observed greater familiarity of users towards common KG entities than towards long-tail items, motivates the use of KG entities for both warm and cold-start recommendations.