Article 70C22 Reading the post-riot posts: how we traced far-right radicalisation across 51,000 Facebook messages

Reading the post-riot posts: how we traced far-right radicalisation across 51,000 Facebook messages

by
Pamela Duncan and Raphael Hernandes
from Technology | The Guardian on (#70C22)

Tracing profiles of those charged with online offences in summer 2024 helped us map a thriving social ecosystem trading far-right sentiment and political disillusionment

More than 1,100 people have been charged in connection to the summer 2024 riots. A small number of them were charged for offences related to their online activity.

Their jail sentences - which ranged from 12 weeks to seven years - became a flashpoint for online criticism. The people behind the posts were variously defended, held up as a cause celebre and cast as political prisoners"; their posts minimised and repeated; their prosecution misrepresented as an attack on free speech (the majority of those prosecuted for online offences faced charges of stirring up racial hatred).

Accuracy (percentage of correctly classified instances): 94.7%.

Precision (percentage of times the True labels assigned by GPT are correct): 79.5.

Recall (percentage of instances classified as True by the humans that were also classified as True by GPT): 86.1%.

F1 (a single percentage that combines precision and recall, higher when GPT both finds the True cases and avoids false alarms): 82.6%.

Continue reading...
External Content
Source RSS or Atom Feed
Feed Location http://www.theguardian.com/technology/rss
Feed Title Technology | The Guardian
Feed Link https://www.theguardian.com/us/technology
Feed Copyright Guardian News and Media Limited or its affiliated companies. All rights reserved. 2025
Reply 0 comments