Deception and rumor detection method based on artificial intelligence optimization algorithm

Today, with the developing technology, access methods to information have also changed. Social networks fill the places of traditional information access tools such as TV, radio, newspaper, magazine. Among the main factors in changing the method of access to information, social networks are cheap, faster access than traditional methods, and easy access from anywhere where the internet is available. It is the accuracy of the information that the social networks or social media are disadvantageous compared to traditional methods. In social media, information spreads so quickly that when it spreads, people unintentionally change the information (rumor event) or information is deliberately served incorrectly for a particular or purpose (deception event). There may be many reasons for the distribution of information in this way, such as commercial, political, and economic. Information with fake content, both rumor and deception purposes, negatively affects both the person who acquires the information and the society. It is extremely important to detect deceptive and rumored information in social networks. In this thesis, Rumor Detection problem and Deception Detection problem which is one of the social network problems are considered as an optimization problem. During the optimization, five heuristic optimization algorithms have been used, three of them have been proposed for the first time in this thesis, which are the new chaotic optimization algorithms and seven supervised artificial intelligence algorithms used in the literature and deception detection and rumor detection results have been compared. Although the method we proposed at the point of solution of the problems is very new, promising results have been obtained.