• DocumentCode
    541786
  • Title

    Ontology based text clustering using the dissimilarity measure

  • Author

    Binisha, R.

  • Author_Institution
    M.E Dept. of CSE, Anna Univ., Tiruchirappalli, India
  • fYear
    2010
  • fDate
    27-29 Dec. 2010
  • Firstpage
    476
  • Lastpage
    480
  • Abstract
    Performance of the text clustering can be improved by using ontologies. Before implementing the clustering process term mutual information matrix is calculated with the aid of the background knowledge build to textual data. Then the K-Modes algorithm is used to cluster the textual data with the dissimilarity measure. This result to obtain clusters with strong intra-similarities and efficiently cluster large textual data.
  • Keywords
    ontologies (artificial intelligence); pattern clustering; text analysis; dissimilarity measure; k-modes algorithm; ontology; term mutual information matrix; text clustering; Algorithm design and analysis; Clustering algorithms; Euclidean distance; Mutual information; Ontologies; Partitioning algorithms; Symmetric matrices; K-Modes; categorical data; clustering; ontology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Communication and Computational Intelligence (INCOCCI), 2010 International Conference on
  • Conference_Location
    Erode
  • Electronic_ISBN
    978-81-8371-369-6
  • Type

    conf

  • Filename
    5738777