Modeling the Post Life Cycle to Estimate the Probability of Epidemics in Online Communities

Using online communities is one of the growing areas for Internet users. In this way, millions of users can be connected indefinitely. In addition to the role of communication, this technology is a treasure of users' perspectives, knowledge and emotions. Such massive content can have many applications in marketing, elearning and e-commerce. In spite of the high number of posts created in online communities, information dissemination faces many problems. The information overload problem in online communities has made it difficult for users to get the right information with their features and interests. Modeling the life cycle of a post provides an opportunity to examine how information is disseminated among users. In these communities, each post after creation is reposted and transmitted by users. This action continues until a post is drowned, that is, when another post is not reinstated. In this paper, the method of modeling the life cycle of posts in online communities is presented. This method is capable of identifying the possibility of an epidemic of a post dynamically at any time. For this purpose, a learning method based on learning automata has been used. The evaluations show that this method is efficient in three evaluation datasets.