Testing the Impact of Semantics and Structure on Recommendation Accuracy and Diversity

TL;DR

This paper investigates how the structure and semantics of Heterogeneous Information Networks influence recommendation accuracy and diversity, finding that network structure plays a more vital role than semantic content.

Contribution

It provides an empirical analysis showing the limited impact of semantic content and highlights the importance of network structure in recommendation performance.

Findings

Network structure significantly affects recommendation accuracy and diversity.

Semantic content has limited influence on recommendation performance.

Shuffling edges to remove semantics does not drastically reduce effectiveness.

Abstract

The Heterogeneous Information Network (HIN) formalism is very flexible and enables complex recommendations models. We evaluate the effect of different parts of a HIN on the accuracy and the diversity of recommendations, then investigate if these effects are only due to the semantic content encoded in the network. We use recently-proposed diversity measures which are based on the network structure and better suited to the HIN formalism. Finally, we randomly shuffle the edges of some parts of the HIN, to empty the network from its semantic content, while leaving its structure relatively unaffected. We show that the semantic content encoded in the network data has a limited importance for the performance of a recommender system and that structure is crucial.