Characterizing Social Bots Spreading Financial Disinformation

Despite the existence of several studies on the characteristics and role of social bots in spreading disinformation related to politics, health, science and education, financial social bots remain a largely unexplored topic. We aim to shed light on this issue by investigating the activities of large social botnets in Twitter, involved in discussions about stocks traded in the main US financial markets. We show that the largest discussion spikes are in fact caused by mass-retweeting bots. Then, we focus on characterizing the activity of these financial bots, finding that they are involved in speculative campaigns aimed at promoting low-value stocks by exploiting the popularity of high-value ones. We conclude by highlighting the peculiar features of these accounts, comprising similar account creation dates, similar screen names, biographies, and profile pictures. These accounts appear as untrustworthy and quite simplistic bots, likely aiming to fool automatic trading algorithms rather than human investors. Our findings pave the way for the development of accurate detection and filtering techniques for financial spam. In order to foster research and experimentation on this novel topic, we make our dataset publicly available for research purposes.