As bots grow increasingly prevalent and sophisticated, it has become harder to distinguish fake Tweets from the authentic Tweets of real users. And no one wants to retweet a bot—doing so is a surefire way to undermine your brand’s credibility, which is never a good look. Luckily, Norton LifeLock’s latest innovation, a tool called Botsight, may be able to help.

How it works

With BotSight, Norton identifies inauthentic Twitter users for you in real time. A simple extension that is compatible with browsers Chrome, Brave, and Firefox, the free tool uses machine learning to analyze and score Twitter accounts based on over 20 different factors. VentureBeat explains:

Powering BotSight is an AI model that detects Twitter bots with a high degree of accuracy, achieving an area under curve — a common indicator of model quality — of 0.967 on research data sets. (A perfect AUC is 1.) In its predictions, it considers over 20 factors, including IP-based correlation (accounts that are closely linked geographically), temporal-based correlation (closely linked in time), signs of automation in usernames and handles (and other metadata), social subgraphs, content similarity, Twitter verification status, the rate at which the account is acquiring followers, and account description.

The scores will then appear next to an icon as a percentage for the account, color-coded to indicate the level of confidence in the account’s authenticity (green = likely an authentic user; red = probably a bot).

Below is an example of what a Tweet might look like your feed with BotSight:

Source: VentureBeat

How to spot a bot

What are some of the characteristics of Twitter bots that flag them as inauthentic users? VentureBeat relates:

Bots generally exhibit regularity in their posting habits that ordinary users don’t, according to NortonLifeLock, and they’re generally short-lived. They also tend to have names containing many numbers and random characters, and they form cliques within which they post identical content.

Technically, BotSight is still considered a research prototype, but it has received positive early reviews from experts in the cybersecurity world. As researchers continue to take steps towards better understanding how bots operate, the tool is a welcome innovation in a world where an estimated 48 million Twitter accounts are bots.