Thursday, July 25, 2024
20.5 C
Los Angeles

How to assess a general-purpose AI model’s reliability before it’s deployed | MIT News

Foundation models are massive deep-learning models that...

El Salvador: Rights Violations Against Children in ‘State of Emergency’

El Salvador’s state of emergency, declared in...

Vietnam: New decree on cashless payments

On 15 May 2024, the Government officially...

BLOC Action Strings for Understanding Social Media Behavior

AI/MLBLOC Action Strings for Understanding Social Media Behavior

Social media is rife with various forms of manipulation, causing harm and financial losses. To tackle this, Alexander Nwala and his team introduced BLOC, a universal framework for describing social media behaviors. Unlike targeting specific actions, BLOC offers a language to identify and understand behaviors. It aids in spotting automated bots and coordinated actions, without classifying them as good or bad.

A user-friendly tool based on BLOC is under development at William & Mary to investigate suspicious account activity. The process involves encoding user actions into BLOC strings, which are then tokenized into words. Machine learning helps classify users into different categories like humans, bots, or “cyborg-like” accounts.

BLOC not only detects bots but also highlights similarities between human-led accounts. It’s versatile and adaptable, making it a valuable tool to combat manipulation in ever-evolving social media landscapes.

Beyond combating bad actors, BLOC has potential applications in studying behavioral shifts related to mental health. However, limitations imposed by social media platforms on data access hinder research efforts, which are crucial for understanding and addressing social media manipulation effectively.


By FCCT Editorial Team

Disclaimer: The views expressed in this article are independent views solely of the author(s) expressed in their private capacity.

Check out our other content


Check out other tags:

Most Popular Articles