Summarizing Web Content to Make Richer RSS Feeds

Abstract

Reading has been one of mankind s favorite activities. Reading can be used to increase their knowledge or for the entertainment. With the popularity of reading many forms of reading material evolved. The conventional methods like books, paper, magazines, journals and new methods like e-books, online magazines, online journals and most importantly web sites are the sources for reading. With the introduction of the web, web sites have been the one of the main means people exchanged knowledge. There is a vast amount of information today in the web that is relevant and irrelevant. Due to this people need to take action to keep up with things that they are interested in. One means would be the use of RSS feed to keep track of web sites of interest. But even those sites do contains unimportant or irrelevant content. The objective of this research is to provide a solution to this issue by enhancing the RSS feed by using web page summarization. In this research current summary production methods are analyzed. Few Novel methods will be introduced using some selected properties of the current methods. The research uses summarization methods used in document summarization in a way applicable to web pages. Summaries will be created using these methods for a document set. The experiment also will conclude by evaluating these method be comparing to actual human generated summaries. The methods will be evaluated using an automated summary evaluation tool.