Taming social bots: Detection, exploration and measurement

Abstract

Social bots have been around since 2008, and thus, they have been polluting our online spaces for over a decade. Social bots are capable of swaying political opinion, spreading false information, and recruiting for terrorist organizations. Social bots use various sophisticated techniques by adopting emotions, sympathy following, synchronous deletions, and profile molting. There are several approaches proposed in the literature for detecting, exploring, and measuring of social bots. We provide a comprehensive overview of the existing work from the data mining and machine learning perspective, discuss relative strengths and weaknesses of various methods, make recommendations for researchers and practitioners, and propose novel directions for future research in taming social bots. This tutorial also discusses pitfalls in collecting and sharing data on social bots.