What is it about?

Currently, there are a lot of social bots acting on different online social networks. Identifying them automatically is a big challenge. This work uses different natural language processing methods to extract characteristics from tweets in order to make the bot detection process more precise. The developed solution uses artificial intelligence techniques, combining feature selection and classification algorithms.

Featured Image

Why is it important?

Social networks, in general, have proven to be quite effective in spreading opinions and influencing people as messages can be shared with thousands of people in a few minutes. However, this ability has been exploited in a negative way, to manipulate opinions and spread misinformation and/or fake news. A common way of doing this is through the use of bots, computer algorithms that mimic human behavior, disseminating topics and news, demonstrating support or rejection to personalities, and interacting with other users, which can impact even democratic discussions. Thus, it is very important to develop automatic mechanisms for detecting these social bots and prevent any harmful behavior.

Perspectives

This work identified several strategies to make the process of automatic detection of social bots more accurate, demonstrating that analyzing the content of tweets provides important information for identifying the behavior of bots. Thus, the work can serve as an inspiration for the development of new bot detection mechanisms. These mechanisms are very important to make discussions on social networks healthier and more democratic.

Dr. Luciano Antonio Digiampietri
Universidade de Sao Paulo Campus da Capital

Read the Original

This page is a summary of: Social bots detection in Brazilian presidential elections using natural language processing, June 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3466933.3466991.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page