Detection of threatening user accounts on Twitter social media database

Abstract

The freedom of social media platforms to post and share daily activities is being misused by threatening users as they post the suspicious and fake content on social media for personal or organisational advantage. This demands to generate a system that can detect suspicious content and their respective user accounts. In this paper, an ant colony optimisation based system for threatening account detection (ACOTAD) is proposed. The connections among the different Twitter users are determined by the pheromone substance secreted by ants on the edges of the path travelled. Better the quality of pheromone indicates the strong connection of one user with another. This research work considers the experimentation on Twitter based Social Honeypot Database. The evaluated results in terms of precision, recall, f-measure, true positive rate, and false positive rate indicate the superiority of the proposed concept in comparison with existing techniques.