FaNDS: Fake News Detection System using energy flow

Recently, the term “fake news” has been broadly and extensively utilized for disinformation, misinformation, hoaxes, propaganda, satire, rumors, click-bait, junk news. It become a serious problem around world. We present new system, FaNDS, that detects fake news efficiently. The system is based on several concepts used in some previous works but different context. There are two main concepts: an Inconsistency Graph Energy Flow. contains items as nodes inconsistent opinions between them edges. Flow assigns each node initial energy then propagated along edges until distribution all converges. To illustrate FaNDS we use original data from Fake News Challenge (FNC-1). First, to be reconstructed order generate Graph. graph various subgraphs with well-defined shapes represent types of connections items. Then method applied. high candidates being In our experiments, these were indeed checked using reliable web sites. compared other detection methods found it more sensitive discovering