Textual documents designed and divided on the Internet are ever changing in various forms. The aim of this project is to characterize and detect personalized and abnormal behaviours of Internet users.It can be applied in many real-life scenarios, such as real-time monitoring on abnormal user behaviours. The existing system of our project works are devoted to topic modelling and the evolution of individual topics, while sequential relations of topics in successive documents published by a specific user are ignored. Hence the users activity monitoring doesn’t feasibly and effectively. We proposed our system to extract the user’s activity on real time web application data set on Twitter and Gmail. Using our technique can monitor the user’s sequential topic pattern based on their session identification on multiple applications with single sign on email id and their session id