Unsupervised rumor detection based on users' behaviors using neural networks

Online social networks have become the hotbeds of many rumors as information can propagate much faster than ever. In order to detect the few but potentially harmful rumors to prevent the public issues they may cause, we propose an unsupervised learning model combining Recurrent Neural Networks and Autoencoders to distinguish rumors as anomalies from other credible microblogs based on users' behaviors. Some features based on comments posted by other users are newly proposed and are then analyzed over their posting time so as to exploit the crowd wisdom to improve the detection performance. The experimental results show that our model achieves a high accuracy of 92.49% and F1 measure of 89.16%. (c) 2017 Elsevier B.V. All rights reserved.