Ricochet: Context and Complementarity-Aware, Ontology-based POIs Recommender System
Post on 08-Aug-2015
- 1. Ricochet: Context and Complementarity-Aware, Ontology-based POIs Recommender System Chun Lu, Philippe Laublet, Milan Stankovic SALAD 2014 May 26th, 2014 Crete, Greece
- 2. Outline Introduction Ricochet system Evaluation Conclusion
- 3. Introduction Point of interest (POI) Increasing popularity of POIs recommender systems Dissatisfaction with recommendations of existing systems
- 4. Whats wrong?
- 5. Whats wrong? Before & after a check-in, recommendations remain unchanged. Research questions User study
- 6. Ricochet System Criteria Contextual criteria Intrinsic criteria Criteria of complementarity
- 7. Ricochet System Criteria of complementarity Each POI category is mapped to a particular feeling. [Savage et al., 2012] Arts & Entertainment = "feeling artsy" Nightlife = "feeling like a party animal" College & Education = "feeling nerdy" Great Outdoors = "feeling outdoorsy" Food = "feeling hungry" Shops = "feeling shopaholic"
- 8. Ricochet System Criteria of complementarity Having a certain feeling Go to a certain POI Visit a POI Having a certain feeling Just-visited POI causes a feeling Going-to POI satisfies it
- 9. Ricochet System Criteria of complementarity Physical activities possess a specific assessable intensity. [Tapia et al., 2007] Intensity of expressiveness Cognitive, emotional, physical POIs classified into four intensity levels Daily life = alternation of different intensities
- 10. Ricochet System Sample of OntoPOI
- 11. Ricochet System Recommendation engine API : Yelp & Jena & Google Maps
- 12. Evaluation Two versions of Ricochet Process Metrics: precision, recall, normalized Discounted Cumulative Gain
- 13. Results The complementarity improves the relevance of the recommendations.
- 14. Conclusion & Future work Ricochet : improve the relevance by considering the complementarity Refine the complementarity Integrate to existing systems
- 15. Questions & Answers Thanks for your attention! Any questions?
View more >
Chapter 7 Context-Aware Recommender Systems ?· Chapter 7 Context-Aware Recommender Systems ... 7 Context-Aware…
An ontology-based context aware system for Selective Dissemination of Information in a digital library
An Ontology for Context-Aware Pervasive Computing finin/papers/ijcai03-ont.pdf · An Ontology for Context-Aware…
A Context-Aware Mobile Recommender System for Context-Aware Mobile Recommender System for Places of Interest Shraddha Borkar, Prof. Roshani Talmale Department of Computer Science and Engineering Tulsiramji Gaikwad Patil College of Engineering Nagpur ...
An Ontology based Context Aware System to Control the ... ?· information to control the movement of…
A Comprehensive Literature Survey of Context-Aware ... phases of a typical context-aware recommender system algorithm are discussed in this section. In Section IV, the three typical context-aware recommender system algorithms are identified and elaborated. Finally, Section V ...
A Cold Start Context-Aware Recommender System Cold Start Context-Aware Recommender System for Tour Planning Using Artificial Neural Network and Case Based Reasoning ZahraBahramian,1 RahimAliAbbaspour,1 andChristopheClaramunt2 1 2 Received 28 April 2017 ...
Chapter 7 Context-Aware Recommender ?· context-aware recommender systems are described in Section 7…
Ontology-Based Context Modeling for a Smart Living we will focus only on ontology-based context ... Ontology-Based Context Modeling for a Smart Living Room ... context modeling approach and a rule based system
An Ontology for Context-Aware Pervasive Computing finin/papers/ · An Ontology for Context-Aware Pervasive…
DRARS, A Dynamic Risk-Aware Recommender system called DRARS (Dynamic Risk-Aware Recommender System), which model the context-aware recommendation as a bandit problem. This system combines a content-based technique and a contextual bandit ...