Deception Detection in Online Media

Abstract Russian Federation and European Union are fighting against fake news among with other counties. The consequences can be observed today in different countries in various topics. The disinformation affected British referendum of existing EU, the US election and Catalonia’s referendum are broadly studied. A need for automated fact-checking increases, European Commission’s Action Plan 8 is an evidence. In this work we develop a model to detect disinformation in Russian language in online media. We use reliable and unreliable sources to compare extracted named entities and verbs. For feature extraction we use DeepPavlov library. The recall for our model is 0.8, in comparison with baseline 0.18. As a baseline we chose Gradient Boosting Machines from Scikit-learn library. We think that media environment is dynamic, thus the automated verification is also should be rapid.