Factorization Machines Leveraging Lightweight Linked Open Data-enabled Features for Top-N Recommendations

TL;DR

This paper demonstrates that Factorization Machines using lightweight, directly accessible LOD-enabled features can achieve competitive top-N recommendation performance without complex graph construction, highlighting the importance of specific feature sets.

Contribution

It introduces a novel approach combining FMs with lightweight LOD features obtained via SPARQL, avoiding graph construction, and evaluates the contribution of different LOD features to recommendation quality.

Findings

FM with lightweight LOD features outperforms other methods on standard datasets.

Property-object lists and PageRank scores significantly improve recommendations.

Subject-property lists do not enhance and may reduce performance.

Abstract

With the popularity of Linked Open Data (LOD) and the associated rise in freely accessible knowledge that can be accessed via LOD, exploiting LOD for recommender systems has been widely studied based on various approaches such as graph-based or using different machine learning models with LOD-enabled features. Many of the previous approaches require construction of an additional graph to run graph-based algorithms or to extract path-based features by combining user- item interactions (e.g., likes, dislikes) and background knowledge from LOD. In this paper, we investigate Factorization Machines (FMs) based on particularly lightweight LOD-enabled features which can be directly obtained via a public SPARQL Endpoint without any additional effort to construct a graph. Firstly, we aim to study whether using FM with these lightweight LOD-enabled features can provide competitive performance compared to a learning-to-rank approach leveraging LOD as well as other well-established approaches such as kNN-item and BPRMF. Secondly, we are interested in finding out to what extent each set of LOD-enabled features contributes to the recommendation performance. Experimental evaluation on a standard dataset shows that our proposed approach using FM with lightweight LOD-enabled features provides the best performance compared to other approaches in terms of five evaluation metrics. In addition, the study of the recommendation performance based on different sets of LOD-enabled features indicate that property-object lists and PageRank scores of items are useful for improving the performance, and can provide the best performance through using them together for FM. We observe that subject-property lists of items does not contribute to the recommendation performance but rather decreases the performance.