Exploiting a Determinant-Based Metric to Evaluate a Word-Embeddings Matrix of Items

In order to generate effective results, it is essential for a recommender system to model the information about the user interests (user profiles). A profile usually contains preferences that reflect the recommendation technique, so collaborative systems represent a user with the ratings given to items, while content-based approaches assign a score to semantic/text-based features of the evaluated items. Even though semantic technologies are rapidly evolving and word embeddings (i.e., vector representations of the words in a corpus) are effective in numerous information filtering tasks, at the moment collaborative approaches (such as SVD) still generate more accurate recommendations. However, this might happen because, by employing classic profiles in form of vectors that collect all the preferences of a user, the power of word embeddings at modeling texts could be affected. In this paper we represent a profile as a matrix of word-embedding vectors of the items a user evaluated, and present a novel determinant-based metric that measures the similarity between an unevaluated item and those in the matrix-based user profile, in order to generate effective content-based recommendations. Experiments performed on three datasets show the capability of our approach to perform a better ranking of the items w.r.t. collaborative filtering, both when compared to a latent-factor-based approach (SVD) and to a classic neighborhood user-based system.

I. Introduction

The rapid growth of the number of companies that perform their activities in the so-called e-commerce environment generates an enormous amount of information, which must be correctly exploited in order to improve the quality and efficiency of the sales criteria [1]. This problem is effectively faced by Recommender Systems [2], which filter the information about their customers in order to get useful elements to produce effective suggestions to them. In order to perform this task, such systems need to define a set of profiles that model the preferences of their customers, and in this context the collaborative techniques, which usually represent a user with the ratings given to the items she evaluated, are in most of the cases more effective than the other techniques. The problem of the data sparsity, a side effect of the collaborative techniques, is effectively faced by the latent-factor-based techniques, such as SVD [3], which nowadays represent the state-of-the-art in this field.