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 filtering 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.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3298689.3347061 | Proceedings of the 13th ACM Conference on Recommender Systems |
Keywords | Field | DocType |
collaborative filtering, recommender systems, user reviews | Recommender system,Data mining,Collaborative filtering,Computer science,Latent variable model,Baseline (configuration management),Artificial intelligence,Generative grammar,Deep learning,Machine learning,Generative model,Text processing | Conference |
ISBN | Citations | PageRank |
978-1-4503-6243-6 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oren Sar Shalom | 1 | 20 | 7.74 |
Guy Uziel | 2 | 0 | 3.04 |
Amir Kantor | 3 | 4 | 0.76 |