Lecture-E2

Lecture-E2 - Lecture E I Tag, You Tag: Translating Tags for...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture E I Tag, You Tag: Translating Tags for Advanced User Models R. Wetzker, C. Zimmermann, C. Bauckhage, and S. Albayrak ACM WSDM, pp. 71-80, 2010
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Introduction Collaborative Tagging Services allow users to label various resources with freely chosen keywords (tags) Problem: Individual users develop highly personalized vocabularies , which meet individual needs and preferences The differences between personal tag vocabularies complicate services, such as social search and tag recommendation Solution: Mapping between personal tags and folksonomies to Infer meaning of user-assigned tags & predict choices of tags Reduce problems related to tag ambiguity , synonymous tags , or multilingualism
Background image of page 2
3 Introduction Tagging Allows users to choose labels that match their needs, tastes, or language Is a powerful alternative to existing taxonomies or predefined dictionaries, which lack flexibility and are expensive to create and maintain Community services that center around tagging resources are called folksonomies, e.g., CiteULike & LibraryThing, which can be classified as Narrow : restrict the tagging of resources to a limited number of users, e,g., photos labeled by owner in Flickr Broad : resources can be tagged by the entire community (i.e., tagging activity of a user can be related to the activity of other users), e.g., Delicious
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 Introduction Concerns with broad folksonomies Each user assign tags for personal content retrieval, developing his/her own tag vocabulary , known as personomies Individual personomies may be difference, e.g., 2 users can bookmark conceptually similar content with dissimilar tags Individual personomies often reflect (i) the multilingualism of users or (ii) their different levels of expertise Resources in broad folksonomies develop a characteristic and stable tag spectrum, which determine the similarity between items Customized tags assignments (TAS) can affect applications developed for personalized tag-based search , tag recommendation , or user-interest discovery User-Centric Tag Model (UCTM)
Background image of page 4
5 User-Centric Tag Model Overcomes problems induced by personomies Derives a translational mapping between individual personomy tags and the corresponding folksonomy to Solve problems related to tag ambiguity , synonymous tags , and biased towards singular or plural form Account for multilingual communities Deduce the meaning of a tag based on who assigned it to over- come inter-user discrepancies in tagging Predict tags that a user will associate with an item based on the association of other users Translational applications Tag Recommendation - suggest potentially relevant tags Social Search - allow users to rely on their own tag vocabularies, which simplifies the talk of searching
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

This document was uploaded on 10/18/2011.

Page1 / 20

Lecture-E2 - Lecture E I Tag, You Tag: Translating Tags for...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online