next up previous
Next: lec26_learnbayes Up: lec26_learnbayes Previous: lec26_learnbayes

Twenty NewsGroups

Given 1000 training documents from each group

Learn to classify new documents according to which newsgroup it came from


comp.graphics misc.forsale
comp.os.ms-windows.misc rec.autos
comp.sys.ibm.pc.hardware rec.motorcycles
comp.sys.mac.hardware rec.sport.baseball
comp.windows.x rec.sport.hockey
   
alt.atheism sci.space
soc.religion.christian sci.crypt
talk.religion.misc sci.electronics
talk.politics.mideast sci.med
talk.politics.misc  
talk.politics.guns  


Naive Bayes: 89% classification accuracy



Don Patterson 2001-12-14