NortonLifeLock has developed a tool that detects bots on Twitter in real-time. Available in beta, the tool is based on a model that the company trained through machine learning to detect Twitter bots with a high degree of accuracy. Called BotSight, the tool is available as a browser extension compatible with Google Chrome and Firefox. The tool works across Twitter screens, including search, trending topics, and home timeline.
“To determine whether an account is a bot, we look at over 20 different distinguishing features per case, including the amount of randomness in the Twitter handle, whether the account is verified, the rate at which it is acquiring followers, and the account’s description. We verified our approach by observing BotSight in action. So far, BotSight’s beta users have successfully analysed over 100,000 Twitter accounts,” Daniel Kats, Principal Researcher NortonLifeLock Research Group wrote in a blogpost.
How It Works
The BotSight annotates each Twitter handle with a bot-probability score directly on the Twitter website. This works across most of Twitter's views including Timeline, Search, Profile, Follower, and clicking on an individual Tweet.
Photo: NortonLifeLockThe scores are generated based on Twitter’s historical data classifier in real-time. The scores are then placed directly onto the page, so you see if you are interacting with a real person or a bot.
Photo: NortonLifeLockIn addition to annotating the Twitter, the BotSight also scan the contents of the Tweet and annotates the multiple mentioned handles in the Tweet's body. It can also annotate retweets and quoted tweets. It works in a variety of Twitter contexts including search, trending topics, and looking at a Tweet's replies. Moreover, the tool can also annotate list of followers and those you follow.
Photo: NortonLifeLockThe tool currently works as browser extension on PCs, and the smartphone app is in works.