An inline, real-time Twitter annotator which computes, for each user in your Twitter feed, the likelihood they are a bot.
BotSight allows you to browse Twitter while annotating each handle with a bot-probability score. This works across most of Twitter's views including Timeline, Search, Profile, Follower, and clicking on an individual Tweet.
The scores are generated by our state-of-the-art classifier in real-time. They are then placed directly onto the page, so you can tell if you're interacting with a real person or a bot.
In addition to annotating the Tweeter, we also scan the contents of the Tweet. For instance, BotSight also annotates mentioned handles in the Tweet's body and the handles in replies. Retweets, quoted tweets, followers, and those you follow are also annotated.
While we do our best to make sure BotSight is accurate, it is still in active development. People may be misclassified as bots or vice-versa.