Abstract
Social media plays the major role in analyzing the user behavior based on the multiple messages given by the users by using social platform. From recent days every user is participating in social media for messaging the hot social topics. These are of two ways, one it considers the multi-message interaction on behavior of the users that participates to analyzes of multi-message interaction that influence the user behavior that shows more accurately. The second stage, using the back-propagation (BP) neural networks the users are managed in multi-message hotspots. In this paper, a new user prediction model is developed for the social hotspots based on a multi-message interaction-driving mechanism (MIDM) which integrates the BP neural network. The performance is calculated based on the improved accuracy.
