SXSW 2023

Disinformation: Identifying Viral Bots and Cyborgs


Under our AI for Good initiative, KUNGFU.AI has analyzed tweets related to the Coronavirus/COVID-19 pandemic and also to the 2022 US mid-term elections in order to find possible patterns of disinformation and unusual propagation of content on Twitter. We used information entropy measures calculated from both the text content and the timing of the tweets to identify accounts displaying significantly more automation than normal Twitter users. We then applied network graph analysis techniques to determine which automated accounts were most successful in getting their content shared or retweeted. We find that cyborgs, actual humans who use special software to control or automate their posts, are generally much more successful than fully automated bots.

Related Media

Additional Supporting Materials


  1. Despite the efforts of social media firms to combat disinformation, many automated accounts escape their detection techniques and can sway the public.
  2. A vast majority of automated accounts that we find are mostly unsuccessful, so its important to focus on the ones that are more successful/
  3. If you identify a tweet spreading disinformation, notify twitter support and report it.



Connor Bibby, Marketing Associate, KUNGFU.AI

Meta Information:

  • Event: SXSW
  • Format: Presentation
  • Track: Tech Industry
  • Track 2
  • Level: Intermediate

Add Comments

comments powered by Disqus

SXSW reserves the right to restrict access to or availability of comments related to PanelPicker proposals that it considers objectionable.