Publication in BibTeX Format

@INPROCEEDINGS{AICPub1806:2010,
  AUTHOR={Madani, O. and Yu, J.},
  TITLE={Discovery of Numerous Specific Topics via Term Co-occurrence Analysis},
  BOOKTITLE={Conference on Information and Knowledge Management (CIKM)},
  YEAR={2010},
  KEYWORDS={unsupervised learning, text mining, co-occurrence graphs, topic discovery,
     tagging, feature induction, feature augmentation},
  ABSTRACT={We describe efficient techniques for construction of large term co-occurrence
     graphs, and investigate an application to the discovery of numerous fine-grained
     (specific) topics. A topic is a small dense subgraph discovered by a random
     walk initiated at a term (node) in the graph. We observe that the discovered
     topics are highly interpretable, and reveal the different meanings of terms
     in the corpus. We show the information-theoretic utility of the topics when
     they are used as features in supervised learning. Such features lead to consistent
     improvements in classification accuracy over the standard bag-of-words representation,
     even at high training proportions. We explain how a layered pyramidal view
     of the term distribution helps in understanding the algorithms and in visualizing
     and interpreting the topics.}
}