Preventing Disinformation through AI


Scientists from the University of Sheffield have developed an innovative AI-based algorithm that will correctly predict which Twitter users will spread the wrong information before they are doing it.

The researchers have found a way of predicting whether a social media user will probably share content from unreliable news sources.

The researchers analyzed over one plus million tweets from approximately 5000 plus Twitter users, thereby processing new innovative natural language processing methods to help computers process and understand vast language data. The tweets they studied were all publicly available tweets for everybody to see on the internet.

Twitter users were divided into two groups as part of the research—those who have shared unreliable/fake news sources and those who only share stories from reliable and trustworthy sources. The data was wont to guide a machine-learning algorithm which will accurately predict(70%) whether a user will repost content from unreliable sources within the future.

The research study found that Twitter users who shared stories from unreliable/fake sources are more likely to share information about politics or religion and use unparliamentary language. They mostly share posts with words such as ‘liberal,” ‘government,” ‘media.”

The study also found that Twitter users who shared stories from reliable news sources often tweeted about their personal lives, such as their emotions and friends’ interactions. This particular group of users often posted tweets with self-twisted words such as

“mood.” “wanna,” “gonna,” “I will,” “excited,” and “birthday.”

Findings from this research could help social media companies such as Twitter and Facebook develop ways to tackle the spread of wrong information online. This helps the social scientists and psychologists improve their understanding of such user behavior on a large scale.

Social media is one of the most used means where people access the media, with millions of users using platforms such as Twitter and Facebook every day to find out about critical news that is happening both locally and internationally. The negative aspect of this is social media has become the primary platform for spreading disinformation, which has a massive impact on society and can influence people’s judgment of what is happening in the world around them.

As part of the research, specific trends are identified in user behavior that could help. Users who share news stories from unreliable sources often tweet about politics or religion. Those people that share stories from reliable/open news platforms often tweeted about their personal lives.

The correlation between the utilization of impolite language and the spread of unreliable content is often attributed to high online political hostility.

Studying and analyzing users’ behavior sharing content from unreliable news sources can help social media platforms eliminate the spread of fake news at the primary user-level concerning the current fact-checking methods that work on the social media posts or the news source level.


Please enter your comment!
Please enter your name here