Information Systems Research
The Journal of Machine Learning Research
Finding high-quality content in social media
WSDM '08 Proceedings of the 2008 International Conference on Web Search and Data Mining
Learning multiple graphs for document recommendations
Proceedings of the 17th international conference on World Wide Web
Bayesian probabilistic matrix factorization using Markov chain Monte Carlo
Proceedings of the 25th international conference on Machine learning
Factorization meets the neighborhood: a multifaceted collaborative filtering model
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Collaborative filtering for orkut communities: discovery of user latent behavior
Proceedings of the 18th international conference on World wide web
Routing Questions to the Right Users in Online Communities
ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
Factor in the neighbors: Scalable and accurate collaborative filtering
ACM Transactions on Knowledge Discovery from Data (TKDD)
Anatomy of the long tail: ordinary people with extraordinary tastes
Proceedings of the third ACM international conference on Web search and data mining
Factorizing personalized Markov chains for next-basket recommendation
Proceedings of the 19th international conference on World wide web
Fast online learning through offline initialization for time-sensitive recommendation
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Soft-constraint based online LDA for community recommendation
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
ValuePick: Towards a Value-Oriented Dual-Goal Recommender System
ICDMW '10 Proceedings of the 2010 IEEE International Conference on Data Mining Workshops
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Commenders: A recommendation procedure for online book communities
Electronic Commerce Research and Applications
A group recommendation system for online communities
International Journal of Information Management: The Journal for Information Professionals
| Hi-index | 0.00 |
Online health communities enable patients to share ideas and experiences to improve their understanding of themselves and their treatment. Personalized recommendation helps patients find appropriate online social resources and protects and enhances the character of the resources. Recommendation needs to leverage a wide variety of types of interactions, but most state-of-the-art recommender systems using matrix factorization are designed for one type of relation with a restricted range of ratings. In this paper, we address the problem of recommendation using multiple relations with unrestricted ranges of ratings derived from social behaviors. We model multiple relations through multi-task matrix factorization where the latent profiles are \emph{partially shared} between relations. Moreover, we offer two new techniques for transforming between the distribution produced by latent factor models and power-law-distributed ratings. The experiments conducted over a data set from a diabetes community suggest that the proposed model can improve the accuracy of recommendation in online health communities. The performance for recommendation to users is very good (mean rank of test examples is less than 5 out of 30) but poorer for recommendation to groups (mean rank 10 out of 30).