Yes. No machine learning model and algorithm is 100% accurate. Periodically, Bot Sentinel will give false positives and false negatives, especially with non-English accounts. We trained Bot Sentinel’s classification model using English tweets, and non-English accounts have a higher rate of false positives. However, the classification model is continually being retrained to improve its accuracy and reliability, and the platform is gradually improving with non-English accounts.
Does Bot Sentinel misclassify accounts? Print
Modified on: Thu, May 28, 2020 at 11:01 AM
Did you find it helpful?Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.