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 mil millones, 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, Reino Unido, Australia and New Zealand. En el futuro, 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, y, 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

Actualmente, la empresa 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 y 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.

A propósito, let’s remind you that another “digital era” has recently ended. Así que, End of an era: Twitter disabled SMS in majority of countries.

Por Vladimir Krasnogolovy

Vladimir es un especialista técnico al que le encanta dar consejos y sugerencias cualificados sobre los productos de GridinSoft. Está disponible las 24 horas del día, los 7 días de la semana para ayudarte con cualquier pregunta relacionada con la seguridad en Internet.

Dejar un comentario

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *