How to Surprisingly Consider Recommendations? A Knowledge-Graph-based Approach Relying on Complex Network Metrics

TL;DR

This paper introduces a knowledge-graph-based recommender system that uses complex network metrics to incorporate a user-defined level of surprise, enhancing the unexpectedness of recommendations beyond traditional similarity-based methods.

Contribution

It proposes a novel reranking approach leveraging network metrics on knowledge graphs to control the surprise level in recommendations, a new perspective in recommender system design.

Findings

Reranking based on network metrics increases recommendation surprise.

The approach is effective on LastFM and synthetic Netflix datasets.

Network metrics influence the degree of recommendation unexpectedness.

Abstract

Traditional recommendation proposals, including content-based and collaborative filtering, usually focus on similarity between items or users. Existing approaches lack ways of introducing unexpectedness into recommendations, prioritizing globally popular items over exposing users to unforeseen items. This investigation aims to design and evaluate a novel layer on top of recommender systems suited to incorporate relational information and suggest items with a user-defined degree of surprise. We propose a Knowledge Graph (KG) based recommender system by encoding user interactions on item catalogs. Our study explores whether network-level metrics on KGs can influence the degree of surprise in recommendations. We hypothesize that surprisingness correlates with certain network metrics, treating user profiles as subgraphs within a larger catalog KG. The achieved solution reranks recommendations based on their impact on structural graph metrics. Our research contributes to optimizing recommendations to reflect the metrics. We experimentally evaluate our approach on two datasets of LastFM listening histories and synthetic Netflix viewing profiles. We find that reranking items based on complex network metrics leads to a more unexpected and surprising composition of recommendation lists.