Experts developed a free bot detection tool on Twitter

Twitter bot detection tool

NortonLifeLock, which appeared after Symantec sold its information security division and brand Symantec Broadcom for $10.7 billion, developed a bot detection tool on Twitter.

Experts have unveiled a beta version of BotSight’s free browser extension that identifies bots on Twitter and is designed to combat fake news and misinformation.

The new tool is already available for Chrome, Brave and Firefox browsers for users from the USA, UK, Australia and New Zealand. In the future, developers also plan to introduce a similar application for smartphones and an extension suitable for Microsoft Edge.

NortonLifeLock experts are now describing BotSight as a research prototype that uses machine learning accurately detect bots on Twitter (including tweets displayed in user feeds, searches, and trends).

The extension analyzes more than 20 different parameters, including the name and description of the account, or number of subscribers increase rate, and, based on this data, determines whether the account is a bot.

“We trained a state-of-the-art machine learning model that can detect Twitter bots with a high degree of accuracy, achieving an Area Under Curve – a common indicator of model quality – of 0.967 on popular research datasets, which matches or exceeds the best current academic results. But we didn’t stop there. We created a tool – called BotSight – which takes the results of our model and injects them directly into the Twitter feed”, — say NortonLifeLock specialists.

By installing the BotSight extension, the user can see a special percent icon (green, yellow or red) next to the name of each Twitter profile. This icon indicates the likelihood that an account manages a real person or a bot.

Twitter bot detection tool

Currently, the company has analyzed with this tool more than 100,000 accounts and found that approximately 5% of the all messages publish bots.

“In a recent analysis of tweets related to coronavirus, we found that between 6 and 18% of users writing on this topic were bots (depending on what time we chose). A random selection from the Twitter stream over the same time showed 4-8% of bots. This contrast demonstrates that bots act strategically: they prefer the latest events in order to maximize their influence”, – said NortonLifeLock experts.

By the way, let’s remind you that another “digital era” has recently ended. So, End of an era: Twitter disabled SMS in majority of countries.

By Vladimir Krasnogolovy

Vladimir is a technical specialist who loves giving qualified advices and tips on GridinSoft's products. He's available 24/7 to assist you in any question regarding internet security.

Leave a comment

Your email address will not be published. Required fields are marked *