Arefeh Esmaili
Interested Fields
IR, ML ,Text Mining ,SNA
Title of Thesis
Presenting an algorithm for source of fake posts detection in social networks using nodes embedding
Description of Thesis
For many years, fake news and messages have been spread in human societies, and today, with the spread of social networks among the people, the possibility of spreading false information has increased more than before. As a result, by disseminating false information throughout social networks, in addition to reducing the credibility of social networks, they endanger the security and privacy of users of these networks. Therefore, identifying fake news and messages has become a prominent issue in the research community. It is also important to identify the users who generate this false information and publish it on the network. This work identifies users who publish incorrect information on the Twitter social network in Persian. In this regard, a system has been established based on combining context-user and context-network properties with the help of a conditional generative adversarial network (CGAN) to balance the data set. The system also detects fake users by modeling the Twitter social network into a graph of user interactions and embedding a node to feature vector by Node2vec. Also, by developing the data set collected at the time of the Kermanshah earthquake period in Iran in 2017 and by conducting several tests, the proposed system has produced good performance results compared to its competitors in detecting fake users in terms of evaluation metrics such as precision, recall, F-measure and accuracy.
Contact Information
Skype: live:.cid.25a8ac8d37211132
arefehesmaili@email.kntu.ac.ir