A multimedia recommender system based on enriched user profiles

Authors:
Marcelo G. Manzato;Rudinei Goularte
Affiliations:
University of Sao Paulo, Sao Carlos, SP, Brazil;University of Sao Paulo, Sao Carlos, SP, Brazil
Venue:
Proceedings of the 27th Annual ACM Symposium on Applied Computing
Year:
2012

Citing 9
Cited 0

Fab: content-based, collaborative recommendation

Communications of the ACM
Multimodal Video Indexing: A Review of the State-of-the-art

Multimedia Tools and Applications
Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions

IEEE Transactions on Knowledge and Data Engineering
Semantic Grounding of Tag Relatedness in Social Bookmarking Systems

ISWC '08 Proceedings of the 7th International Conference on The Semantic Web
Matrix Factorization Techniques for Recommender Systems

Computer
Social tagging in recommender systems: a survey of the state-of-the-art and possible extensions

Artificial Intelligence Review
User profiles for personalized information access

The adaptive web
Review: review of the state of the art: Discovering and associating semantics to tags in folksonomies

The Knowledge Engineering Review
Creating peer-level video annotations for web-based multimedia

EGMM'04 Proceedings of the Seventh Eurographics conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a multimedia recommender system which is based on user profiles enriched with peer-level annotations. Our annotation-based filtering algorithm is able to reduce the effects of two well-known problems inherent to recommender systems: the new user problem and over-specialization. In the first case, we propose a mechanism to enrich new user profiles with concepts gathered from folksonomies. In the second, our system uses genres and/or categories associated to each item in order to accomplish better recommendations. We present the results comparing our approach with other systems previously reported on literature.