Extract and rank web communities

Asif Salekin, Jeniya Tabassum, Binte Jafar, Masud Hasan

Research output: Chapter in Book/Entry/PoemConference contribution

Abstract

A web community is a pattern in the WWW which is understood as a set of related web pages. In this paper, we propose an efficient algorithm to find the web communities on a given specific topic. Instead of working on the whole web graph, we work on a web domain, which we extract based on the topic specific search results. Therefore, the resulted communities are highly related with the search topic. The ranking of a community denotes the degree of relevance between the search query and the extracted communities. We introduce an approach for ranking the extracted communities based on their dense bipartite pattern. Ranking significantly improves the relevance of the extracted communities with the search topic.

Original languageEnglish (US)
Title of host publication3rd International Conference on Web Intelligence, Mining and Semantics, WIMS 2013
PublisherAssociation for Computing Machinery
ISBN (Print)9781450318501
DOIs
StatePublished - 2013
Externally publishedYes
Event3rd International Conference on Web Intelligence, Mining and Semantics, WIMS 2013 - Madrid, Spain
Duration: Jun 12 2013Jun 14 2013

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Web Intelligence, Mining and Semantics, WIMS 2013
Country/TerritorySpain
CityMadrid
Period6/12/136/14/13

Keywords

  • Dense bipartite graph
  • Domain graph
  • Ranking web communities
  • Structured web search
  • Web community
  • Web graph

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Extract and rank web communities'. Together they form a unique fingerprint.

Cite this