Entropy based feature selection for text categorization - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Entropy based feature selection for text categorization

Christine Largeron
Christophe Moulin
Mathias Géry
  • Function : Correspondent author
  • PersonId : 843869

Connectez-vous pour contacter l'auteur


In text categorization, feature selection can be essential not only for reducing the index size but also for improving the performance of the classi er. In this article1, we propose a feature selection criterion, called Entropy based Category Coverage Di erence (ECCD). On the one hand, this criterion is based on the distribution of the documents containing the term in the categories, but on the other hand, it takes into account its entropy. ECCD compares favorably with usual feature selection methods based on document frequency (DF), information gain (IG), mutual information (IM), 2, odd ratio and GSS on a large collection of XML documents from Wikipedia encyclopedia. Moreover, this comparative study con rms the e ectiveness of selection feature techniques derived from the 2 statistics.
Fichier principal
Vignette du fichier
sac_2011.pdf (112.95 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00617969 , version 1 (31-08-2011)



Christine Largeron, Christophe Moulin, Mathias Géry. Entropy based feature selection for text categorization. ACM Symposium on Applied Computing, Mar 2011, TaiChung, Taiwan. pp.924-928, ⟨10.1145/1982185.1982389⟩. ⟨hal-00617969⟩
111 View
5949 Download



Gmail Mastodon Facebook X LinkedIn More