Information Evaluation Based on Sources Dependence

Many data management applications require integrating data from multiple sources.Each of these sources provides a set of values and different sources can often provide conflicting values.To present quality data to users,it is critical that data integration systems can resolve conflicts and discover true values.In this paper,we improve the existing algorithm with using a new voting algorithm and considering the diverse expressions of the same value,e.g.person's name.The experiment results shown it is very effective for discovering true values among conflicting values.