Text Classification

Introduction

The Text Classification Package (also called Live HTML Text Classification)

HTML Text can be classified using the dca::HtmlTextClassifier class. A dca::HtmlText object must first be created from HTML data. The HtmlTextClassifier analyses the data and returns a classification as a dca::TextClassificationResults object.

The HTML input data must be valid and complete.

HTML text can be currently classified as one of the following categories:

• CATEGORY_ID_TEXT_PORNOGRAPHY
• CATEGORY_ID_TEXT_WAREZ
• CATEGORY_ID_TEXT_GAMBLING
• CATEGORY_ID_TEXT_ANONYMOUS_PROXIES
• CATEGORY_ID_TEXT_ILLEGAL_DRUGS
• CATEGORY_ID_TEXT_WEAPONS

Classes
class	dca::TextClassification
	The HTML Text Classification module class. More...
class	dca::TextClassificationResult
	Single result of a text classification. More...
class	dca::TextClassificationResults
	Overall results of a text classification. More...
class	dca::HtmlTextClassifier
	HTML text classifier object for text classification. More...

Files
file	text_classification.h
	Package header file for the Text Classification module.
file	text_classification_result.h
	Single result of a text classification.
file	text_classification_results.h
	Overall results of a text classification.
file	text_classifier.h
	HTML text classification class.