Probabilistic graphical models for multi-source fusion from text sources

In this paper we present probabilistic graph fusion algorithms to support information fusion and reasoning over multi-source text media. Our methods resolve misinformation by combining knowledge similarity analysis and conflict identification with source characterization. For experimental purposes, we used the dataset of the articles about current military conflict in Eastern Ukraine. We show that automated knowledge fusion and conflict detection is feasible and high accuracy of detection can be obtained. However, to correctly classify mismatched knowledge fragments as misinformation versus additionally reported facts, the knowledge reliability and credibility must be assessed. Since the true knowledge must be reported by many reliable sources, we compute knowledge frequency and source reliability by incorporating knowledge provenance and analyzing historical consistency between the knowledge reported by the sources in our dataset.