Authors: Mosab Khayat, Morteza Karimzadeh, Jieqiong Zhao, David Ebert
Abstract: Social media applications such as Twitter are filled with Spambots. Detecting these malicious accounts are essential yet challenging as they continually evolve and evade traditional detection techniques. In this work, we propose VASSL, a visual analytics tool that aims at assisting the detection and labeling process. Our tool enhances the performance and the scalability of manual labeling by providing multiple connected views and utilizing dimensionality reduction, sentiment analysis and topic modeling techniques which provide new insights that enable discriminating spambots. The tool allows users to select and analyze groups of accounts in an interactive manner, which would allow for detecting spambots that cannot be identified when examined individually.