ISSearch
Interface ISFeatureInterface

All Superinterfaces:

Serializable

All Known Implementing Classes:

ISFeature

public interface ISFeatureInterface

extends Serializable

This interface prescribes the general structure of document features for the ISSearch search engine.

Method Summary

double	getRTF() Returns the Relative Term Frequency (RTF) weight of the feature in the document.
String	getTerm() Returns the term that is represented by this feature in the bag-of-words model.
double	getTF() Returns the absolute Term Frequency (TF) weight of the feature in the document.

Method Detail

getTerm

public String getTerm()

Returns the term that is represented by this feature in the bag-of-words model. For compatibility reasons, we assume that all features are word stems generated by the Porter stemming algorithm from original words of the document after stopword removal. We also assume that all terms are converted to lowercase and trimmed usind String.toLowerCase() and String.trim() functions.

Returns:

The term that is represented by this feature.

getTF

public double getTF()

Returns the absolute Term Frequency (TF) weight of the feature in the document. TF is defined as the total number of term occurences in the current document.

Returns:

The document-specific TF weight of the feature.

getRTF

public double getRTF()

Returns the Relative Term Frequency (RTF) weight of the feature in the document. RTF is defined as RTF / N, where N is the total number of terms in the current document.

Returns:

The document-specific RTF weight of the feature.