DPITT: Multi-viewpoint visualization system for detecting peculiar WWW pages rapidly

Masayuki Hirose, Einoshin Suzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we present a visualization method for detecting peculiar WWW pages given a set of keywords. Detection of peculiar WWW pages is expected to lead to making profits by various means including business and investment. We try to capture peculiarity of a WWW page from several viewpoints at summary levels by using GF (Google Frequency) method to detect rare words and the PLSI (Probabilistic Latent Semantic Indexing) method to find the major topic and the remaining topic. Experimental results show that our visualization method DPITT (Detecting Peculiar pages from Image, Topic and Term) outperforms Google in a problem setting which favors the latter considerably.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Granular Computing
Pages538-541
Number of pages4
Publication statusPublished - 2006
Externally publishedYes
Event2006 IEEE International Conference on Granular Computing - Atlanta, GA, United States
Duration: May 10 2006May 12 2006

Other

Other2006 IEEE International Conference on Granular Computing
CountryUnited States
CityAtlanta, GA
Period5/10/065/12/06

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Hirose, M., & Suzuki, E. (2006). DPITT: Multi-viewpoint visualization system for detecting peculiar WWW pages rapidly. In 2006 IEEE International Conference on Granular Computing (pp. 538-541). [1635859]