My name is Christopher Bouzy, and I launched Bot Sentinel to help diminish the effectiveness of propaganda bot/troll accounts that infest Twitter. I believe Twitter users should be able to engage in healthy online discourse without foreign countries and organized groups manipulating the conversation.
Bot Sentinel was designed to be easy to use and also to be as informative as possible. Twitter accounts the system is tracking are publicly displayed to give visitors of this website a better understanding of how bot/troll accounts spread disinformation, and to be as transparent as possible. The accounts listed on this website are tracked and updated daily.
Bot Sentinel is not a partisan platform; we track both left and right bot/troll accounts. The system uses machine learning and artificial intelligence to classify Twitter accounts that exhibit bot/troll behavior, and accounts that exceed a certain threshold are then added to a publicly available database that anyone can browse.
Bot Sentinel was trained to identify specific types of bot/troll accounts using thousands of accounts and millions of tweets for our machine learning model. The system can correctly identify propaganda bot/troll accounts with an accuracy of 98%. Unlike other machine learning tools designed to detect bots, we are not sacrificing accuracy for speed. We analyze hundreds of Tweets per each Twitter account to determine if an account exhibit irregular tweet activity or engaging in harassment.
Most accounts tracked by Bot Sentinel belong to a vast network of bot/troll accounts intended to deceive other Twitter users. However, not every account classified as a bot/troll is part of a network or some conspiracy.
In the future, I will add more details here, but until then I hope you find this platform to be useful and if you have any questions, please feel free to contact me!