Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

TL;DR

This paper investigates how the semantics of item co-occurrence influence recommendation performance in set completion tasks, emphasizing the roles of data sparsity, input size, and multiple data modalities.

Contribution

It introduces an analysis of autoencoder-based models for set completion, highlighting the importance of co-occurrence semantics and the effective use of metadata across different scenarios.

Findings

Supplying the partial item set improves relatedness-based recommendations.

Metadata enhances diversity-based recommendations.

Autoencoders perform comparably to simple co-occurrence models, with added flexibility.

Abstract

We address the problem of recommending relevant items to a user in order to "complete" a partial set of items already known. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender performance. We also investigate data sparsity through a pruning parameter and the influence of using additional metadata. As recommender models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. This outcome means that the semantics of item co-occurrence is an important factor. The simple item co-occurrence model is a strong baseline for citation recommendation. However, autoencoders have the advantage to enable exploiting additional metadata besides the partial item set as input and achieve comparable performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the result. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate recommendation model and carefully decide which metadata to exploit.