You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2-1Lines changed: 2 additions & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,5 @@
1
-

1
+

2
+
2
3
# Using Genetic Algorithm for feature selection in text dataset
3
4
This project presents a wrapper approach of feature selection using a genetic algorithm. The multinomial event model of Naïve Bayes was used as a fitness function to determine the selected features of the documents. Different experiments have been performed on the 20newsgroups dataset to see the impact of the population size and the number of generations. The experiments were compared with the classification without feature selection using different evaluation metrics. All the experiment results showed that feature selection using the genetic algorithm will positively affect the classification performance.
0 commit comments