What is it about?
Social bots (algorithms that control profiles) are very active on social networks, for example, spreading fake news, viruses, or several kinds of scams. This work combines different strategies to increase the performance of bot detection algorithms. In particular, the users' profiles are clustered and a classification model, using artificial intelligence, is created for each cluster. The proposed approached was tested considering users that tweet about COVID-19, and it overperformed the related approaches.
Featured Image
Photo by Luke Chesser on Unsplash
Why is it important?
Detecting bots in social networks is very important to prevent their harmful actions. Allowing real users to act in a more carefree way on social networks and favoring democratic debates.
Perspectives
Online social networks bring an excellent opportunity for brainstorming, giving a voice to many people who were previously virtually invisible to society. On the other hand, social networks have been used to manipulate public opinion and disseminate fake news. Providing mechanisms to enrich respectful and democratic debate is a major challenge that needs to be undertaken by each one of us.
Dr. Luciano Antonio Digiampietri
Universidade de Sao Paulo Campus da Capital
Read the Original
This page is a summary of: Combining clustering and classification algorithms for automatic bot detection: a case study on posts about COVID-19, June 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3466933.3466970.
You can read the full text:
Resources
Contributors
The following have contributed to this page
