0411075 20240103182259.920060210235959.9 3-540-40217-9 Berlin Springer 2003 8 s. Lecture Notes in Computer Science. 2652 646-653PeralesF. J.CampilhoA. J. C. text classification multinomial mixture model Bhattacharyya distance cav_un_auth*0101171 Novovičová Jana UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101155 Malík Antonín UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. 09K 12B IAA2075302 GA AV ČR cav_un_auth*0001801 KSK1019101 GA AV ČR cav_un_auth*0000219 CEZ:AV0Z1075907 The mixture of multinomial distributions is proposed as a model for class-conditional distributions in document classification task. Experimental results on the Reuters and the Newsgroups data sets indicate the effectiveness of the multinomial mixture model. Furthermore, an increase in classification accuracy is achieved for small training data sets, when multiclass Bhattacharyya distance is used instead of average mutual information as a feature selection criterion. cav_un_auth*0213025 Iberian Conference on Pattern Recognition and Image Analysis. IbPRIA 2003 /1./ Puerto de Andratx ES 04.06.2003-06.06.2003 BB RO http://hdl.handle.net/11104/0131162 UTIA-B 20030062 2003 2003 Berlin Springer 3-540-40217-9 Pattern Recognition and Image Analysis 646 653 Perales F. J. 340 Campilho A. J. C. 340