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
, an independent military force, and allied militias in Sudan raped several dozen women and girls in West Darfur’s capital, El Geneina, and those fleeing to Chad between late April and late June 2023, Human Rights Watch said today. The assailants appear to have targeted people because of their Massalit ethnicity and, in some cases, because they were known activists.){kind=link}