Improving web search by categorization, clustering, and personalization

Zhu, Dengya; Dreher, Heinz

doi:10.1007/978-3-540-88192-6_69

117988_Zhu%20%20Dreher%20ADMA%2008_09may09_CameraReady.pdf (105.7Kb)

Access Status

Open access

Authors

Zhu, Dengya

Dreher, Heinz

Date

2008

Type

Conference Paper

Metadata

Show full item record

Citation

Zhu, Dengya and Dreher, Heinz. 2008. Improving web search by categorization, clustering, and personalization, in Tang, C. and Ling, C. and Zhou, X. and Cercone, N. and Li, X. (ed), Advanced Data Mining and Applications: Proceedings of the 4th International Conference, ADMA 2008, pp. 659-666, Oct 8-10 2008. Chengdu, China.

Source Title

Proceedings of the 4th international conference on advanced data mining and applications 2008(ADMA 2008)

Source Conference

4th international conference on advanced data mining and applications 2008(ADMA 2008)

DOI

10.1007/978-3-540-88192-6_69

ISBN

9783540881919

Faculty

School of Information Systems

Science and Engineering

Remarks

The original publication is available at http://link.springer.com/

URI

http://hdl.handle.net/20.500.11937/43954

Collection

Curtin Research Publications

Abstract

This research combines Web snippet1 categorization, clustering and personalization techniques to recommend relevant results to users. RIB - Recommender Intelligent Browser which categorizes Web snippets using socially constructed Web directory such as the Open Directory Project (ODP) is to bedeveloped. By comparing the similarities between the semantics of each ODP category represented by the category-documents and the Web snippets, the Web snippets are organized into a hierarchy. Meanwhile, the Web snippets are clustered to boost the quality of the categorization. Based on an automatically formed user profile which takes into consideration desktop computer informationand concept drift, the proposed search strategy recommends relevant search results to users. This research also intends to verify text categorization, clustering, and feature selection algorithms in the context where only Web snippets are available.