linked open data-enabled strategies for top-n recommendations

Click here to load reader

Post on 01-Jul-2015

1.066 views

Category:

Documents

1 download

Embed Size (px)

DESCRIPTION

Linked Open Data-enabled Strategies for Top-N Recommendations - Cataldo Musto, Pierpaolo Basile, Pasquale Lops, Marco De Gemmis and Giovanni Semeraro - 1st Workshop on New Trends in Content-based Recommender Systems, co-located with ACM Recommender Systems 2014

TRANSCRIPT

  • 1. CBRecSys 2014Workshop on New Trends inContent-based Recommender SystemsFoster City (CA, United States)October 6, 2014Linked Open Data-enabledStrategies for Top-NRecommendationsCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis(Universit degli Studi di Bari Aldo Moro, Italy - SWAP Research Group)

2. Outline Background Content-based RecSys (CBRS) Limitations Linked Open Data What? Introducing LOD in CBRS Experiments ConclusionsCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.2 Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 3. Content-based Recommender SystemsSuggest items similar to those the user liked in the past(I bought Converse shoes, Ill continue buying similar sport shoes)Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.3 Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 4. Content-based Recommender SystemsLimitationsLimited content4(in several domains)Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 5. Content-based Recommender SystemsLimitationsPoor SemanticsCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.5 Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 6. How can we boostContent-basedRecommender Systemswith Semantics?(and with more content)6ProblemCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 7. 7Semantics in CBRS State of the artOntologies XFolksonomies Distributional SemanticsEncyclopedic Knowledge Linked Open DataCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 8. 8Top-down approachesWhat is the difference?XFormal Semantics Large-scaleFolksonomies X XOntologies V XEncyclopedic Knowledge X VDistributional Semantics X VLinked Open Data V VCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 9. 9Top-down approachesWhat is the difference?XFormal Semantics Large-scaleFolksonomies X XOntologies V XEncyclopedic Knowledge X VDistributional Semantics X VLinked Open Data V VLinked Open Data merge the vastness of encyclopedic knowledgewith the formal semantics typical of ontologiesCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 10. 10Top-down approachesWhat is the difference?XWe focus on the introduction ofFormal Semantics Large-scaleFolksonomies X XLinked Open Data inOntologies V XContent-based RecommenderEncyclopedic Knowledge X VSystemsDistributional Semantics X VLinked Open Data V VLinked Open Data merge the vastness of encyclopedic knowledgewith the formal semantics typical of ontologiesCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 11. 11Linked Open DataWhat are we talking about?Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 12. 12Linked Open DataDefinitionMethodology to publish, share and linkstructured data on the WebCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 13. 13Linked Open Data (cloud)What is it?A (large) set of interconnected semantic datasetsCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 14. 14Linked Open Data (cloud)What kind of datasets?Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 15. 15Linked Open Data (cloud)DBpediahttp://dbpedia.orgCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 16. 16Linked Open Data (cloud)http://dbpedia.orgDBpediaDBpedia is the structured mapping of WikipediaIt is the core of the LOD cloud.Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 17. 17Linked Open Data (cloud)Example: unstructured content from WikipediaexampleFoster City is a town in United States located in California(from Wikipedia page)Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 18. 18Linked Open Data (cloud)How are these data represented?Semantic Web cakeInformation from theLOD cloud isrepresented in RDFCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 19. Foster City is a town in United States located in California19Linked Open Data (cloud)How are these data represented?Foster City United Stateshttp://dbpedia.org/resource/United_StatesCaliforniahttp://dbpedia.org/resource/Foster_City,_Californiahttp://dbpedia.org/resource/Californiadbpedia-owl:countrydbpedia-owl:isPartOfexample(from Wikipedia page)Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 20. Foster City is a town in United States located in California20Linked Open Data (cloud)How are these data represented?Data coming from the LOD cloud have aformal semantics represented in RDFFoster City United Stateshttp://dbpedia.org/resource/United_StatesCaliforniahttp://dbpedia.org/resource/Foster_City,_Californiahttp://dbpedia.org/resource/Californiadbpedia-owl:countrydbpedia-owl:isPartOfexample(from Wikipedia page)Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 21. 21Our checklistCan Linked Open Data boostcontent-based recommender systems?More Semantics More ContentV ?Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 22. 22Linked Open Data (cloud)How many data?Cataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 23. 23Linked Open Data (cloud)How many data?1048 datasets and 58 billions triplessource: http://stats.lod2.euCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 24. 24Our checklistCan Linked Open Data boostcontent-based recommender systems?More Semantics More ContentV VCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 25. 25Our checklistCan Linked Open Data boostcontent-based recommender systems?More Semantics More ContentV VbutCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 26. 26Research QuestionCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 27. 27ApproachWe propose two methodologies tointroduce LOD-based features into CBRSDirect Access to DBpedia Entity Linking algorithmsCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 28. Introducing LOD-based features in CBRS28Methodology :: Direct Access to DBpedia(We assume that each item to be recommender is already in the LOD cloud)The simplest way to introduce LOD-based featuresDomain-dependent featuresare manually defined1.2.(e.g. book recommendation > genre, author, publisher, subject, etc.)SPARQL queries extract features valuesCataldo Musto, Pierpaolo Basile, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis.Linked Open Data-enabled Strategies for Top-N Recommendation. CBRecSys 2014 Workshop, Silicon Valley (US), 6.10.2014 29. Introducing LOD-based features in CBRSExample: The Great and Secret Show (Clive Barkers book)29Methodology :: Direct Access to DBpediaCataldo Musto, Pierpaolo Basile, Gio

View more