Temporal top-k search in social tagging sites using multiple social networks

Authors:
Wenyu Huo;Vassilis J. Tsotras
Affiliations:
Department of Computer Science and Engineering, University of California, Riverside, CA;Department of Computer Science and Engineering, University of California, Riverside, CA
Venue:
DASFAA'10 Proceedings of the 15th international conference on Database Systems for Advanced Applications - Volume Part I
Year:
2010

Citing 4
Cited 2

IR evaluation methods for retrieving highly relevant documents

SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Optimal aggregation algorithms for middleware

PODS '01 Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Modern Information Retrieval

Modern Information Retrieval
Efficient top-k querying over social-tagging networks

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval

A social inverted index for social-tagging-based information retrieval

Journal of Information Science
Discerning actuality in backstage: comprehensible contextual aging

EC-TEL'12 Proceedings of the 7th European conference on Technology Enhanced Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In social tagging sites, users are provided easy ways to create social networks, to post and share items like bookmarks, videos, photos and articles, along with comments and tags. In this paper, we present a study of top-k search in social tagging sites by utilizing multiple social networks and temporal information. In particular, besides the global connection, we consider two main social networks, namely the friendship and the common interest networks in our scoring functions. Based on the degree of participation in various networks, users can be categorized into specific classes that differ in their weights on each scoring component. Temporal information, usually ignored by previous works, can enhance the popularity and freshness of the ranking results. Experiments and evaluations on real social tagging datasets show that our framework works well in practice and give useful and intuitive results.