Skip to main content

Table 4 Notation use for feature selection

From: An ensemble approach to stabilize the features for multi-domain sentiment analysis using supervised machine learning

Symbol Description
Nall The total no. of documents in training dataset
Ni No. of documents in class ci
Wi No. of documents in class ci contain feature f
Xi No. of documents not in class ci but contain feature f
Yi = Ni − Wi No. of documents in class ci don’t contain feature f
Zi = Nall − Ni − Xi No. of documents neither in class ci nor contain the feature f