Learning distributed representations from reviews for collaborative filtering

Amjad Almahairi, Kyle Kastner, Kyunghyun Cho, Aaron Courville

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased exibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model's ability to act as a regularizer of the product representations.

Original languageEnglish (US)
Title of host publicationRecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages147-154
Number of pages8
ISBN (Electronic)9781450336925
DOIs
StatePublished - Sep 16 2015
Event9th ACM Conference on Recommender Systems, RecSys 2015 - Vienna, Austria
Duration: Sep 16 2015Sep 20 2015

Publication series

NameRecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems

Other

Other9th ACM Conference on Recommender Systems, RecSys 2015
Country/TerritoryAustria
CityVienna
Period9/16/159/20/15

Keywords

  • Deep learning
  • Neural networks
  • Recommender systems

ASJC Scopus subject areas

  • Information Systems
  • Software
  • Computer Science Applications
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Learning distributed representations from reviews for collaborative filtering'. Together they form a unique fingerprint.

Cite this