What is it about?
Social bots are diverse. We introduce a machine learning model that improves the chances to detect social bots different from known bots in the training data. This model is behind the current version of the popular Botometer tool, which researchers and social media users employ to better understand the role of bots in spreading information.
Featured Image
Photo by Kevin Ku on Unsplash
Why is it important?
We are vulnerable to manipulation on social media. Tools to detect inauthentic accounts can help us spot this abuse.
Perspectives
Platforms are removing inauthentic accounts more aggressively, but it's an arms race and some bots evade detection. People should be aware of potential deception online.
Filippo Menczer
Indiana University System
Read the Original
This page is a summary of: Detection of Novel Social Bots by Ensembles of Specialized Classifiers, October 2020, ACM (Association for Computing Machinery),
DOI: 10.1145/3340531.3412698.
You can read the full text:
Contributors
The following have contributed to this page
