Effective Suppression of False Rumors in Social Network Service

This paper considers the problem of suppressing the spread of false tweet in SNS (Social Networking Service) which would cause serious damages to the users such as defamation and bankruptcy. The idea of the proposed method is to inject warning tweet to the social network so that the spread of the false tweet is effectively suppressed. More concretely, we notify the warning tweet to the users who received the false tweet but did not retweet it. The performance of the proposed method is evaluated by simulations. The result of simulations indicate that the proposed injection method reduces the spread of false tweet to 20% of un-injected case and the effect of suppression is maximized when the injection to the followees of target users is repeated at an early stage of the spreading of false tweet.