A Semantic Hybrid Approach for Sound Recommendation

  title={A Semantic Hybrid Approach for Sound Recommendation},
  author={Vito Claudio Ostuni and T. D. Noia and Eugenio Di Sciascio and Sergio Oramas and Xavier Serra},
  journal={Proceedings of the 24th International Conference on World Wide Web},
  • V. Ostuni, T. D. Noia, X. Serra
  • Published 18 May 2015
  • Computer Science
  • Proceedings of the 24th International Conference on World Wide Web
In this work we describe a hybrid recommendation approach for recommending sounds to users by exploiting and semantically enriching textual information such as tags and sounds descriptions. As a case study we used Freesound, a popular site for sharing sound samples which counts more than 4 million registered users. Tags and textual sound descriptions are exploited to extract and link entities to external ontologies such as WordNet and DBpedia. The enriched data are eventually merged with a… 

Figures from this paper

A Semantic-Based Approach for Artist Similarity
The evaluation results show that an approach that computes similarity over a graph of entities and semantic categories clearly outperforms a baseline that exploits word co-occurrences and latent factors.
Graph Based Recommendations: From Data Representation to Feature Extraction and Application
A novel generic approach for uncovering latent preference patterns from user data is proposed and evaluated, which relies on representing the data using graphs, and then systematically extracting graph-based features and using them to enrich the original user models.
A New Hybrid Collaborative Recommender Using Semantic Web Technology and Demographic data
A new hybrid CF approach is presented that exploits Semantic Web Technology as well as demographic data to alleviate all the problems mentioned above and the experimental results on the MovieLens dataset verify the effectiveness and efficiency of the approach.
Learning to Identify Complementary Products from DBpedia
This work proposes a framework that aims at alleviating problems by exploiting a knowledge graph (DBpedia) in addition to products’ available information such as titles, descriptions and categories rather than transactions to predict complementary products for an unseen set of products.
Feeding a Hybrid Recommendation Framework with Linked Open Data and Graph-Based Features
A hybrid recommendation framework based on classification algorithms such as Random Forests and Naive Bayes, which are fed with several heterogeneous groups of features, which is split into two classes: classic features, as popularity-based, collaborative and content-based ones, and extended features gathered from the LOD cloud, as basic and graph-based features.
Knowledge acquisition in the information age: the interplay between lexicography and natural language processing
This dissertation presents several improvements in NLP tasks such as Definition andHypernym Extraction, Hypernym Discovery, Taxonomy Learning or KB construction and completion, and in all of them they take advantage of knowledge repositories of various kinds, showing that these are essential enablers in text understanding.
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-based Features
Results show that both LOD-based and graph-based features positively affect the overall performance of the algorithm, especially in highly sparse recommendation scenarios, thus confirming the insights behind this research.
Recommender Systems Leveraging Multimedia Content
A thorough review of the state-of-the-art of recommender systems that leverage multimedia content is presented, by classifying the reviewed papers with respect to their media type, the techniques employed to extract and represent their content features, and the recommendation algorithm.
A semantic-enhanced trust based recommender system using ant colony optimization
This paper proposes a novel trust-based approach, called Semantic-enhanced Trust based Ant Recommender System (STARS), which satisfies all the properties of trust and performs a depth- first search for the optimal trust paths in the trust network and selects the best neighbors of an active user to provide better recommendations.


Extending Tagging Ontologies with Domain Specific Knowledge
Preliminary research is described around the idea of extending tagging ontologies by incorporating some domain specific class definitions and relations to bring more meaningful structure into folksonomies and improve browsing and organisation functionalities of online platforms relying on tagging systems.
Entity Linking meets Word Sense Disambiguation: a Unified Approach
Babelfy is presented, a unified graph-based approach to EL and WSD based on a loose identification of candidate meanings coupled with a densest subgraph heuristic which selects high-coherence semantic interpretations.
A Linked Data Recommender System Using a Neighborhood-Based Graph Kernel
This paper presents a CB-RS that leverages LOD and profits from a neighborhood-based graph kernel that is able to compute semantic item similarities by matching their local neighborhood graphs.
Hybrid Recommender Systems: Survey and Experiments
  • R. Burke
  • Computer Science
    User Modeling and User-Adapted Interaction
  • 2004
This paper surveys the landscape of actual and possible hybrid recommenders, and introduces a novel hybrid, EntreeC, a system that combines knowledge-based recommendation and collaborative filtering to recommend restaurants, and shows that semantic ratings obtained from the knowledge- based part of the system enhance the effectiveness of collaborative filtering.
BPR: Bayesian Personalized Ranking from Implicit Feedback
This paper presents a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem and provides a generic learning algorithm for optimizing models with respect to B PR-Opt.
Sparse linear methods with side information for top-n recommendations
A set of sparse linear methods with side information (SSLIM) is proposed, which involve a regularized optimization process to learn a sparse aggregation coefficient matrix based on both user-item purchase profiles and item side information.
Evaluation of recommendations: rating-prediction and ranking
This paper examines both rating prediction and ranking approaches in detail, and finds that the dominating difference lies instead in the training and test data considered: rating prediction is concerned with only the observed ratings, while ranking typically accounts for all items in the collection, whether the user has rated them or not.