A Semantic Hybrid Approach for Sound Recommendation
作者： Vito Claudio Ostuni , Tommaso Di Noia , Eugenio Di Sciascio , Sergio Oramas , Xavier Serra
关键词:
摘要: In this work we describe a hybrid recommendation approach for recommending sounds to users by exploiting and semantically enriching textual information such as tags descriptions. As case study used Freesound, popular site sharing sound samples which counts more than 4 million registered users. Tags descriptions are exploited extract link entities external ontologies WordNet DBpedia. The enriched data eventually merged with domain specific tagging ontology form knowledge graph. Based on latter, recommendations then computed using semantic version of the feature combination approach. An evaluation historical shows improvements respect state art collaborative algorithms.
poliba.it参考文章(7)
Vito Claudio Ostuni, Tommaso Di Noia, Roberto Mirizzi, Eugenio Di Sciascio, A Linked Data Recommender System using a Neighborhood-based Graph Kernel international conference on electronic commerce. pp. 89- 100 ,(2014) , 10.1007/978-3-319-10491-1_10
Sergio Oramas, Frederic Font, Xavier Serra, György Fazekas, Extending tagging ontologies with domain specific knowledge international semantic web conference. pp. 209- 212 ,(2014)
Robin Burke, Hybrid Recommender Systems: Survey and Experiments User Modeling and User-adapted Interaction. ,vol. 12, pp. 331- 370 ,(2002) , 10.1023/A:1021240730564
Xia Ning, George Karypis, Sparse linear methods with side information for top-n recommendations Proceedings of the sixth ACM conference on Recommender systems - RecSys '12. pp. 155- 162 ,(2012) , 10.1145/2365952.2365983
Harald Steck, Evaluation of recommendations: rating-prediction and ranking conference on recommender systems. pp. 213- 220 ,(2013) , 10.1145/2507157.2507160
Andrea Moro, Alessandro Raganato, Roberto Navigli, Entity Linking meets Word Sense Disambiguation: A Unified Approach Transactions of the Association for Computational Linguistics. ,vol. 2, pp. 231- 244 ,(2014) , 10.1162/TACL_A_00179
Lars Schmidt-Thieme, Zeno Gantner, Steffen Rendle, Christoph Freudenthaler, BPR: Bayesian personalized ranking from implicit feedback uncertainty in artificial intelligence. pp. 452- 461 ,(2009)