Communications of the ACM
AI Can Predict Twitter Users Likely to Spread Disinformation Before They Do It
Artificial intelligence at The University of Sheffield predicts the likelihood of Twitter users spreading disinformation.
Artificial intelligence developed by researchers at The University of Sheffield in the U.K. predicted the likelihood of Twitter users spreading disinformation, using natural language processing techniques to analyze about 1 million tweets.
The researchers grouped about 6,200 users into those who share unreliable news sources and those who only share stories from reliable sources.
They trained a machine learning algorithm on that data to predict whether users will repost content from unreliable sources later. The predictions were later found to be 79.7% accurate.
Users who shared stories from unreliable sources were more likely to tweet about politics or religion, using impolite language; those who shared stories from reliable sources frequently tweeted about their personal lives.
Sheffield's Yida Mu said, "Studying and analyzing the behavior of users sharing content from unreliable news sources can help social media platforms to prevent the spread of fake news at the user level, complementing existing fact-checking methods that work on the post or the news source level."
From The University of Sheffield (U.K.)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found