System and method for detecting personal experience event reports from user generated internet content

Abstract

A method implementable on a computing device for scoring segments of Internet posts is disclosed. The method includes defining a set of indicating factors where each indicating factor is associated with a possible feature in the segments, and where possible features affect a likelihood that the Internet posts represent a user generated product personal experience event report associated with a pre-defined search subject.

What is claimed is: 
     
         1 . A method for scoring segments of Internet posts, implementable on a computing device, the method comprising:
 defining a set of indicating factors, wherein each said indicating factor is associated with a possible feature in the segments, and   wherein said possible features affect a likelihood that the Internet posts represent a user generated product personal experience event report associated with a pre-defined search subject.   
     
     
         2 . A method according to  claim 1  comprising:
 weighting said indicating factors in accordance with said likelihood, wherein each of said indicating factors is at least one of a negative and a positive value. 
 
     
     
         3 . A method for scoring segments of Internet posts, implementable on a computing device, the method comprising:
 listing factors detected in text segments of the Internet posts, defining weights to be associated with each of said factors, wherein each defined weight reflects a value for an associated factor as a predictor of the segments representing a user generated product personal experience event report; and   multiplying a ratio of said weighted factors, divided by an overall number of words in the segment.