DMCA
Probabilistic models for unified collaborative and content-based recommendation in sparsedata environments (2001)
Cached
Download Links
| Venue: | In UAI ’01, 437–444 |
| Citations: | 170 - 9 self |
BibTeX
@INPROCEEDINGS{Popescul01probabilisticmodels,
author = {Rin Popescul and Lyle H. Ungar},
title = {Probabilistic models for unified collaborative and content-based recommendation in sparsedata environments},
booktitle = {In UAI ’01, 437–444},
year = {2001}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Recommender systems leverage product and community information to target products to consumers. Researchers have developed collaborative recommenders, content-based recommenders, and a few hybrid systems. We propose a unified probabilistic framework for merging collaborative and content-based recommendations. We extend Hofmann’s (1999) aspect model to incorporate three-way co-occurrence data among users, items, and item content. The relative influence of collaboration data versus content data is not imposed as an exogenous parameter, but rather emerges naturally from the given data sources. However, global probabilistic models coupled with standard EM learning algorithms tend to drastically overfit in the sparsedata situations typical of recommendation applications. We show that secondary content information can often be used to overcome sparsity. Experiments on data from the ResearchIndex library of Computer Science publications show that appropriate mixture models incorporating secondary data produce significantly better quality recommenders than-nearest neighbors (-NN). Global probabilistic models also allow more general inferences than local methods like-NN. 1
Keyphrases
content-based recommendation sparsedata environment probabilistic model global probabilistic model recommender system leverage product relative influence content-based recommenders appropriate mixture model item content community information secondary data three-way co-occurrence data sparsedata situation researchindex library collaborative recommenders hybrid system exogenous parameter unified probabilistic framework data source collaboration data versus content data secondary content information standard em learning algorithm quality recommenders than-nearest neighbor local method general inference recommendation application computer science publication
