Evaluating the maximum confidence of facts for information provided on the web

Ace p.

Order the writing of a tailor-made Computer science Term papers

Free quote online

Thesis Format .pdf

Evaluating the maximum confidence of facts for information provided on the web

Download

Read an extract

Reader
Abstract
Contents
Extract

Abstract

The World Wide Web is an important information source for us. But, there is no guarantee for the relevance of information retrieved from the Web. The information provided by one Website may be conflicting with the information on the property of an object from other website. In this paper, we study a concept, called Veracity, i.e. conformity to truth, which studies how to find true facts from a large amount of conflicting information of an object, provided by various websites. The TCRC (Trustworthiness and Confidence based on Ratio contribution) algorithm, which considers the relationships between websites and their information and evaluate the confidence of facts and trustworthiness of websites from Ratio Contribution of the facts for that website.

Index Terms: Web mining, Graph Theory, Relevant information.

Abstract
Introduction
Problem definition
1. Basic definitions
2. Basic assumptions
Computational model
1. Fact confidence and website trustworthiness
2. Basic inference
3. Influences between facts
Implementational details
Conclusion
References

Get this table of contents for free after login.

Extract

[...] Thus considering the facts and influence between the facts, trustworthiness of websites and confidence of a fact can me maximized. Table Conflicting information about the players websites Sheetudeep Headlinesindia Altiusdirectory players R.T.Pointing, A.Symonds M.S.Dhoni, M.E.K Hussey,Yuvraj Singh M.S.Dhoni, C.H.Gayle,M.E.K Hussey Thatscricket.oneindia.in M.S.Dhoni, M.E.K.Hussey Yuvraj Singh All37 Ricky Pointing, Micheal Hussey, Gambir 2. PROBLEM DEFINITIONS In this paper, we study the problem of finding true facts and trustworthiness for websites Basic Assumptions Assumption 1.Usually there is only one true fact for a property of an object. [...]

[...] w Website Set of facts provided by w f Fact in(f) Influence score Adjusted influence score The set of websites providing f The object f is about Imp(fi->fj) Influence between the facts Weight of object about same object ρ d Max difference between two iterations Adjusted confidence of fact 3.1 Fact Confidence Trustworthiness and Website We first discuss how to infer website trustworthiness and fact confidence from each other Basic Inference As defined in Definition the trustworthiness of a website is the contribution of facts at instant pointed by the website. [...]

[...] The trust worthiness of a website w is the ratio contribution of confidence of the facts which the websites point to and is denoted by tw(w). The Influence between the facts may exist and is indicated as, if first website indicates that the author of the book is “Jennifer Widom,” which is fact f1. The second website says that there are two authors “Jennifer Widom and Stefano which is fact f2. If f2 is correct, then f1 is incomplete and will have low confidence, and thus, Imp(f2 f1) is low. [...]

[...] Web sites Facts f1 Objects w1 w2 w For any value of influence score the confidence of a fact is greater than zero. So even for negative influence score the confidence score is positive and greater than but not zero CONCLUSION In this paper, we study and formulate the Veracity problem, which aims at resolving conflicting facts from multiple websites and finding the true facts among them. We propose TCRC, an approach that utilizes the interdependency between website trustworthiness and fact confidence to find trustable websites with ratio contribution and true facts. [...]

pdf