Method And System For Scoring Credibility Of Information Sources

Abstract

A method for classifying information sources and content based on credibility, reliability, or trust. A content item describing an event is retrieved from an information provider and parsed for links. Each link is evaluated and attributed a sentiment score. The same event is identified in a set of know sources and an event score is calculated based on the credibility of each of the known sources. Finally, the content item is ranked based on the event and sentiment scores.

Description

FIELD OF THE INVENTION[0001]The present invention relates generally to information extraction. More particularly, the present invention relates to classifying or ranking information sources and events during extraction.BACKGROUND OF THE INVENTION[0002]The internet is one of the primary sources of information of modern life. However, on the web, there coexists a lot of valuable, useful and accurate information together with misleading or inaccurate information. There also exists sources of information that are more trusted and those that are less trusted, and other sources which cannot readily be identified as trusted or not trusted. General web-based searching can return information that is harmful or misleading. The use of non-credible sources of information as basis for decisions can have a severe impact in fields like politics, health, finance and many others. For instance, in the 2008 U.S. presidential campaign of Barack Obama, misleading information connecting the future presid...

AI Technical Summary

Benefits of technology

The present invention provides a method for ranking information based on the credibility of sources and the probability that the information is true or reliable. The method extracts content from information sources, parses them for source links, and assigns a sentiment score to each link based on the likelihood of the source being a known good or bad source. The method also calculates an event score for each event based on the likelihood of the event being reliable, and combines these scores to determine the overall reliability of the information. The method can be implemented on a computer-readable medium and can be used to rank information based on the likelihood of its accuracy.

Problems solved by technology

However, on the web, there coexists a lot of valuable, useful and accurate information together with misleading or inaccurate information.

General web-based searching can return information that is harmful or misleading.

The use of non-credible sources of information as basis for decisions can have a severe impact in fields like politics, health, finance and many others.

For instance, in the 2008 U.S. presidential campaign of Barack Obama, misleading information connecting the future president to a Muslim faith organization resulted in substantial confusion among voters.

Various other instances of false or misleading reports emanating from the internet have been document, and have had consequences affecting lives and decisions.

On top of this, there is some amount of inaccurate or mistrusted information that cannot be properly described as spam.

As is evident, prior art approaches have been suitable for ranking web pages and providing a list of hits in response to a search request, but are inadequate for assessing the reliability of the information, the reliability of the links to other sources on web pages, or the reliability of events being described with sufficient confidence to permit decision-makers to rely on this information without a significant due diligence burden.

Images