Co-preserving patterns in bipartite partitioning for topic identification

Tianming Hu, Hui Xiong, Sam Yuan Sung

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

3 Scopus citations


The claimed advantage of describing a document data set with a bipartite graph is that partitioning such a graph yields a co-clustering of words and documents. The topic of each cluster can then be represented by the top words and documents that have highest within- cluster degrees. However, such claims may fail if top words and documents are selected simply because they are very general and frequent. In addition, for those words and documents across several topics, it may not be proper to assign them to a single cluster. To that end, this paper introduces a new bipartite formulation that incorporates both word hypercliques and document hypercliques as super vertices. By copreserving hypercliqiie patterns during the clustering process, our experiments on real-world data sets show that better clustering results can be obtained and the cluster topic can be more precisely identified. Also, we illustrate an application of the partitioned bipartite to search engines, returning clustered search results for keyword queries. We show that the topic of each cluster with respect to the current query can be identified more accurately with the words and documents from the patterns than with those top ones from the standard bipartite formulation.

Original languageEnglish (US)
Title of host publicationProceedings of the 7th SIAM International Conference on Data Mining
PublisherSociety for Industrial and Applied Mathematics Publications
Number of pages6
ISBN (Print)9780898716306
StatePublished - 2007
Event7th SIAM International Conference on Data Mining - Minneapolis, MN, United States
Duration: Apr 26 2007Apr 28 2007

Publication series

NameProceedings of the 7th SIAM International Conference on Data Mining


Other7th SIAM International Conference on Data Mining
Country/TerritoryUnited States
CityMinneapolis, MN

All Science Journal Classification (ASJC) codes

  • Engineering(all)


  • BipartitepPartitioning
  • Co-clustering
  • Hyperclique pattern
  • Pattern preserving
  • Topic identification


Dive into the research topics of 'Co-preserving patterns in bipartite partitioning for topic identification'. Together they form a unique fingerprint.

Cite this