Weighted Document Frequency for Feature Selection in Text Classification

In the past research, Document Frequency (DF) has been validated to be a simple yet quite effective measure for feature selection in text classification. The calculation is based on how many documents in a collection contain a feature, which can be a word, a phrase, a n-gram, or a specially derived attribute. The counting process takes a binary strategy: if a feature appears in a document, its DF will be increased by one. This traditional DF metric concerns only about whether a feature appears in a document, but does not consider how important the feature is in that document. Obviously, thus counted document frequency is very likely to introduce much noise. Therefore, a weighted document frequency (WDF) is proposed and expected to reduce such noise to some extent. Extensive experiments on two text classification data sets demonstrate the effectiveness of the proposed measure.