BibTeX
@MISC{Wei_datacorpus:,
author = {Lu Wei and Advisor Dr. Min-yen Kan and Lu Wei},
title = {Data Corpus: 1 CD By},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Web pages often embed scripts for a variety of purposes, including advertising and dynamic interaction. Understanding embedded scripts and their purposes can often help to interpret or provide crucial information about the web page. I have developed a functionality-based categorization of JavaScript, the most widely used web page scripting language. I then view understanding embedded scripts as a text categorization problem. I show how traditional information retrieval methods can be augmented with the features distilled from the domain knowledge of JavaScript and program analysis to improve classification performance. I perform experiments on the standard WT10G web page corpus, and show that my techniques eliminate over 50 % of errors over a standard text classification baseline. Subject Descriptors:
Keyphrases
web page data corpus dynamic interaction embedded script program analysis traditional information retrieval method standard text classification baseline domain knowledge classification performance subject descriptor functionality-based categorization text categorization problem standard wt10g web page corpus crucial information
