WebSum: enhanced SumBasic algorithm for Web site summarization

Jason Yong Jin Tee, Lay Ki Soon, Choo Yee Ting

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

Due to the rapid increase of information in the World Wide Web, there exists an explosion of information on the Web that may overwhelm the common Web user. The Web user may find it quicker or more efficient to browse the Web by reading summaries of Web sites. This paper proposes WebSum to compress Web site content into a summary. WebSum is an enhancement of the SumBasic algorithm, that was mainly used for multi-document summarization. In the case of Web sites, we find that several Web characteristics such as title and keywords can be used to extract sentences that may represent the overall topic of the Web site. Initial results show that WebSum is able to reveal sentences relate to the concept of the Web site. WebSum is then evaluated against the original algorithm of SumBasic.

Original languageEnglish
Title of host publicationProceedings - 2012 4th Conference on Data Mining and Optimization, DMO 2012
Pages137-142
Number of pages6
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventConference on Data Mining and Optimization 2012 - Langkawi, Malaysia
Duration: 2 Sept 20124 Sept 2012
Conference number: 4th
https://ieeexplore.ieee.org/xpl/conhome/6322848/proceeding (Proceedings)

Publication series

NameConference on Data Mining and Optimization
ISSN (Print)2155-6938
ISSN (Electronic)2155-6946

Conference

ConferenceConference on Data Mining and Optimization 2012
Abbreviated titleDMO 2012
Country/TerritoryMalaysia
CityLangkawi
Period2/09/124/09/12
Internet address

Cite this