From Word Embeddings to Item Recommendation

TL;DR

This paper explores applying Word2Vec, a natural language processing technique, to recommendation systems using non-textual check-in data from Foursquare, demonstrating promising results in venue recommendation accuracy.

Contribution

It introduces a novel application of Word2Vec to recommendation systems with non-textual data, expanding its use beyond traditional NLP tasks.

Findings

Word2Vec representations improve venue recommendation accuracy.

Continuous vector space models show promise for recommendation tasks.

Application to Foursquare data validates the approach.

Abstract

Social network platforms can use the data produced by their users to serve them better. One of the services these platforms provide is recommendation service. Recommendation systems can predict the future preferences of users using their past preferences. In the recommendation systems literature there are various techniques, such as neighborhood based methods, machine-learning based methods and matrix-factorization based methods. In this work, a set of well known methods from natural language processing domain, namely Word2Vec, is applied to recommendation systems domain. Unlike previous works that use Word2Vec for recommendation, this work uses non-textual features, the check-ins, and it recommends venues to visit/check-in to the target users. For the experiments, a Foursquare check-in dataset is used. The results show that use of continuous vector space representations of items modeled by techniques of Word2Vec is promising for making recommendations.