1 / 57

Helping online communities to semantically enrich folksonomies

Helping online communities to semantically enrich folksonomies. Freddy Limpens , Fabien Gandon Edelweiss, INRIA Sophia Antipolis { freddy.limpens , fabien.gandon}@inria.fr Michel Buffa Kewi , I3S, Univerité Nice-Sophia Antipolis. Edelweiss. ISICIL, mai 2010. How to turn

yoshi-hardin
Download Presentation

Helping online communities to semantically enrich folksonomies

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Helping online communities to semantically enrich folksonomies Freddy Limpens, Fabien Gandon Edelweiss, INRIA Sophia Antipolis {freddy.limpens,fabien.gandon}@inria.fr Michel Buffa Kewi, I3S, UniveritéNice-Sophia Antipolis Edelweiss ISICIL, mai 2010

  2. How to turn folksonomies ... ? Energy pollutant related related pollution ...into comprehensible topic structures ? has narrower Soil pollutions

  3. … without overloading users

  4. … and by collecting all user's expertise into the process

  5. Our approach Integrate usage-analysis for a tailored solution Supporting diverging points of view Automaticprocessings + Human expertise through user-friendly interfaces

  6. Concrete scenario Archivists centralize + tag Experts produce docs + tag Public audience read + tag

  7. 1. Modelingstatements about tags

  8. Supporting diverging points of view skos:related pollution car

  9. Supporting diverging points of view skos:related pollution car disagrees agrees John Paul

  10. Supporting diverging points of view tagSemanticStatement (named graph) skos:related pollution car hasApproved hasRejected Paul John

  11. Supporting diverging points of view

  12. 2. folksonomyenrichmentLife cycle

  13. Dataset

  14. Folksonomy enrichment life-cycle Flat folksonomy User-centric structuring Automatic processing Detectconflicts ADDING TAGS Global structuring Structuredfolksonomy

  15. 1. String-based metrics pollution pollution pollution pollution pollution Soil pollutions pollution pollutant

  16. Evaluation of 30 edit distances Combining the best metrics Needs complement ! 1. String-based metrics

  17. 1. String-based metrics EvaluatedagainstAdemeexpert's point of view

  18. Result on full dataset Related 55,10% Broader/narrower 32% CloseMatch 12,82%

  19. Result on full dataset Node size ↔ InDegree ◉ tags (delicious + thesenet) ◉mot-cléssvic

  20. Result on full dataset Node size ↔ InDegree ◉ tags (delicious + thesenet) ◉mot-cléssvic

  21. 2. Tri-partite structure offolksonomies • Association via : • Users • tags Fig. Markines et al. (2009)

  22. 2. Tri-partite structure of folksonomies Tag-based association : => gives "related" relations

  23. Exampleresult on CADIC dataset:

  24. 2. Tri-partite structure of folksonomies User-based association (Mika) : environnement agriculture U3 U1 U6 U2 U4 => gives "subsumption" relations

  25. Exampleresult on Deliciousdataset: Arrowsmean "has broader" thickness ≈ weight

  26. TheseNetdataset: Arrowsmean "has broader" thickness ≈ weight

  27. Folksonomy enrichment life-cycle Flat folksonomy User-centric structuring Automatic processing Detectconflicts ADDING TAGS Global structuring Structuredfolksonomy

  28. Embedding structuring tasks within everyday activity (searching e.g)

  29. Embedding structuring tasks within everyday activity (searching e.g)

  30. Capturing user's point of view

  31. Experimentation ADEME

  32. Folksonomy enrichment life-cycle Flat folksonomy User-centric structuring Automatic processing Detectconflicts ADDING TAGS Global structuring Structuredfolksonomy

  33. Conflict detection narrower pollution environment broader

  34. Conflict detection narrower pollution environment broader Using rules e.g: IFnum(narrower)/num(broader) ≥ c THENnarrowerwins ELSE 'more generic' wins

  35. Conflict detection narrower pollution environment related broader related more generic more generic narrower broader

  36. Ademeexperimentation

  37. Exampleresult on Ademe'sexperimentationsubset

  38. Exampleresult on Ademe'sexperimentationsubset

  39. Folksonomy enrichment life-cycle Flat folksonomy User-centric structuring Automatic processing Detectconflicts ADDING TAGS Global structuring Structuredfolksonomy

  40. Global structuring by Referent related pollution environment hasApproved ReferentUser

  41. Folksonomy enrichment life-cycle Flat folksonomy User-centric structuring Automatic processing Detectconflicts ADDING TAGS Global structuring Structuredfolksonomy

  42. environment environment environment narrower pollutants pollution pollution pollution pollutants Referent Paul John narrower related narrower environment narrower pollution pollutants

  43. Take away message (conclusion)

  44. What we do : Help communities structure their tags

  45. Our contributions: Usagesanalysis Automatic processing of tags Tag structuring embedded in every-day tools Supporting multi-points of view

  46. Future work Interfaces : to capture user-centric contributions Global administrations (Referent User) Tag searching Real-scaleexperimentation Mappingbetweenknowledgerepresentation(Gemet thesaurus – Tags – CADIC e.g.) Moving to othersocio-structuralmodels

  47. Thank you ! freddy.limpens@inria.fr http://www-sop.inria.fr/members/Freddy.Limpens/ http://isicil.inria.fr

  48. What is a tag ?

  49. Tagging model

More Related