MindReader: Recommendation over Knowledge Graph Entities with Explicit User Ratings

TL;DR

This paper introduces the MindReader dataset with explicit user ratings for both items and knowledge graph entities, demonstrating its benefits for improving recommendation models in the movie domain.

Contribution

The paper presents a new dataset with explicit ratings for KG entities and items, and shows how including non-item entity ratings enhances recommendation quality.

Findings

Including non-item entity ratings improves recommendation accuracy.

Non-item ratings can replace item ratings without performance loss.

Users are more familiar with KG entities than long-tail items.

Abstract

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.