Answers are grounded in this paper and cite their sources.
A considerable amount of data in social networks like Twitter is not generated by humans but by automatic programs (bots). Some of these bots are mimicking humans (socialbots) and can hardly be identified. In this article, we analyze a social botnet involved in the Ukrainian/Russian conflict. Based on text mining and unsupervised learning, we can identify three different behaviors: mimicry, window dressing, and reverberation.
No takes yet. Share an insight, caveat, or question.
Hegelich et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: