What is a Social Media Bot? A Global Comparison of Bot and Human Characteristics

TL;DR

The paper defines a first-principles social media bot and performs a large-scale, cross-event analysis over roughly $5\text{B}$ tweets from about $2\times10^8$ users labeled by BotHunter, revealing that bots constitute about $20\%$ of users on average and spike during high-salience events. It systematically compares bots and humans across four axes—linguistic cues, self-presentation of identity, and social interactions—finding consistent distinctions: bots exhibit more automated linguistic patterns, denser and more star-like ego-networks, and narrower identity repertoires, contrasted with humans who show richer dialogue and broader identities. The study also probes bot evolution, showing detectors are challenged by evasion tactics and Generative AI–driven content, while BotHunter can still identify a substantial fraction of bots (though with variable scores). It proposes a Detect–Differentiate–Disrupt framework, offers practical recommendations for leveraging bots for social good and moderating malicious bots, and outlines open challenges and future directions, including cross-platform generalization and policy implications.

Abstract

Chatter on social media is 20% bots and 80% humans. Chatter by bots and humans is consistently different: bots tend to use linguistic cues that can be easily automated while humans use cues that require dialogue understanding. Bots use words that match the identities they choose to present, while humans may send messages that are not related to the identities they present. Bots and humans differ in their communication structure: sampled bots have a star interaction structure, while sampled humans have a hierarchical structure. These conclusions are based on a large-scale analysis of social media tweets across ~200mil users across 7 events. Social media bots took the world by storm when social-cybersecurity researchers realized that social media users not only consisted of humans but also of artificial agents called bots. These bots wreck havoc online by spreading disinformation and manipulating narratives. Most research on bots are based on special-purposed definitions, mostly predicated on the event studied. This article first begins by asking, "What is a bot?", and we study the underlying principles of how bots are different from humans. We develop a first-principle definition of a social media bot. With this definition as a premise, we systematically compare characteristics between bots and humans across global events, and reflect on how the software-programmed bot is an Artificial Intelligent algorithm, and its potential for evolution as technology advances. Based on our results, we provide recommendations for the use and regulation of bots. Finally, we discuss open challenges and future directions: Detect, to systematically identify these automated and potentially evolving bots; Differentiate, to evaluate the goodness of the bot in terms of their content postings and relationship interactions; Disrupt, to moderate the impact of malicious bots.

Figures (15)

• Figure 1: Definition of Social Media Bot. This definition displays the possibilities of mechanics that the bot account can carry out. A bot does not necessarily carry out all the mechanics.
• Figure 2: Illustration of multidisiplinary methods used for our analysis
• Figure 3: Comparison of Bot volume across events. The percentage of bot users across the events are on average around 20%.
• Figure 4: Comparison of psycholinguistic overall cue usage (average cue usage per user) by bots and humans across datasets. Green cells show that humans use a larger number of the cue. Red cells show that bots use a larger number of the cue. * within the cells indicates there is a significant difference in the usage of the cue between bots and humans at the $p<0.05$ level.
• Figure 5: Comparison of identity-related behaviors in bots and humans. The Methods section explains the derivation of the identity categories and topic frames.