A generative model for review-based recommendations

Oren Sar Shalom, Guy Uziel, Amir Kantor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

User generated reviews is a highly informative source of information, that has recently gained lots of attention in the recommender systems community. In this work we propose a generative latent variable model that explains both observed ratings and textual reviews. This latent variable model allows to combine any traditional collaborative fltering method, together with any deep learning architecture for text processing. Experimental results on four benchmark datasets demonstrate its superiority comparing to all baseline recommender systems. Furthermore, a running time analysis shows that this approach is in order of magnitude faster that relevant baselines. Moreover, underlying our solution there is a general framework that may be further explored.

Original languageEnglish
Title of host publicationRecSys 2019 - 13th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages353-357
Number of pages5
ISBN (Electronic)9781450362436
DOIs
StatePublished - 10 Sep 2019
Externally publishedYes
Event13th ACM Conference on Recommender Systems, RecSys 2019 - Copenhagen, Denmark
Duration: 16 Sep 201920 Sep 2019

Publication series

NameRecSys 2019 - 13th ACM Conference on Recommender Systems

Conference

Conference13th ACM Conference on Recommender Systems, RecSys 2019
Country/TerritoryDenmark
CityCopenhagen
Period16/09/1920/09/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computing Machinery.

Keywords

  • Collaborative Filtering
  • Recommender Systems
  • User Reviews

Fingerprint

Dive into the research topics of 'A generative model for review-based recommendations'. Together they form a unique fingerprint.

Cite this