Research Repository

A local information passing clustering algorithm for tagging systems

Zong, Yu, Xu, Guandong, Jin, Ping, Dolog, Peter and Jiang, Shan (2011) A local information passing clustering algorithm for tagging systems. In: Database Systems for Advanced Applications : 16th International Conference, DASFAA 2011 : InternationalWorkshops - GDB, SIM3, FlashDB, SNSMW, DaMEN, DQIS : Hong Kong, China, April 22-25, 2011 : Proceedings. Xu, Jianliang, Yu, Ge, Zhou, Shuigeng and Rainer, Unland, eds. Lecture notes in computer science, 6637 . Springer, pp. 333-343.

Full text for this resource is not available from the Research Repository.

Abstract

Under social tagging systems, a typical Web2.0 application, users label digital data sources by using tags which are freely chosen textual descriptions. Tags are used to index, annotate and retrieve resource as an additional metadata of resource. Poor retrieval performance remains a major problem of most social tagging systems resulting from the severe difficulty of ambiguity, redundancy and less semantic nature of tags. Clustering method is a useful tool to increase the ability of information retrieval in the aforementioned systems. In this paper, we propose a novel clustering algorithm named LIPC (Local Information Passing Clustering algorithm). The main steps of LIPC are: (1) we estimate a KNN neighbor directed graph G of tags and calculate the kernel density of each tag in its neighborhood; (2) we generate local information, local coverage and local kernel of each tag; (3) we pass the local information on G by I and O operators until they are converged and tag priory are generated; (4) we use tag priory to find out the clusters of tags. Experimental results on two real world datasets namely MedWorm and MovieLens demonstrate the efficiency and the superiority of the proposed method.

Item Type: Book Section
ISBN: 9783642202438 (print), 9783642202445 (online)
Uncontrolled Keywords: ResPubID22966, social networking, networks, annotation, social tagging, tag vector, tag similarity, directed graphs, experimental datasets
Subjects: Faculty/School/Research Centre/Department > School of Engineering and Science
FOR Classification > 0806 Information Systems
SEO Classification > 8902 Computer Software and Services
Depositing User: VUIR
Date Deposited: 10 Jan 2013 22:01
Last Modified: 21 Mar 2013 22:44
URI: http://vuir.vu.edu.au/id/eprint/9483
DOI: https://doi.org/10.1007/978-3-642-20244-5
ePrint Statistics: View download statistics for this item
Citations in Scopus: 2 - View on Scopus

Repository staff only

View Item View Item

Search Google Scholar