Follow Us:
Saturday, August 13, 2022

New way to identify credible tweets may combat ‘fake news’

Scientists have identified words and phrases that predict the credibility of posts on Twitter that may help tackle the menace of 'fake news'.

By: PTI |
January 29, 2017 11:31:16 am
credible words,credible posts, credible tweets, fake news, linguistics, words used in tweets, retweets, lower credibility scores, credibility on social media, fake news, fake news on social media, how to identify fake news, Twitter, Twitter words identified, credible Twitter words, Science, Science news  Tweets with booster words were seen as credible but those mocking the impracticality of the event were seen as less credible. (Picture for representation, Source: AP)

Scientists, including one of Indian origin, have identified words and phrases that predict the credibility of posts on microblogging site Twitter, an advance that may help tackle the menace of ‘fake news’.

The findings suggest that the words of millions of people on social media have considerable information about an event’s credibility – even when an event is still ongoing.

Watch all our videos from Express Technology

“There have been many studies about social media credibility in recent years, but very little is known about what types of words or phrases create credibility perceptions during rapidly unfolding events,” said Tanushree Mitra, a PhD candidate at Georgia Institute of Technology, who led the research.

Subscriber Only Stories
Re-Defining The Tradition In Folk Art: An Art Educator’s PerspectivePremium
Symbiosis School of Sports Sciences (SSSS) launches undergraduate program...Premium
MIT World Peace University launches Five-Year Integrated B.Tech with MBA ...Premium
Bring Home The Ultimate Solution For The Whole Family With Airtel Xstream...Premium

The team looked at 66 million tweets surrounding 1,400 real-world events in 2014 and 2015, including the emergence of Ebola in West Africa, the Charlie Hebdo attack in Paris and the death of Eric Garner in New York City.They asked people to judge the posts on their credibility (from “certainly accurate” to “certainly inaccurate”).

Then the team fed the words into a model that split them into 15 different linguistic categories. The classifications included positive and negative emotions, hedges and boosters, and anxiety.The system then examined the words to judge if the tweets were credible or not. It matched the humans’ opinions about 68 per cent of the time. That is significantly higher than the random baseline of 25 per cent, researchers said.

Also Read:  Twitter releases documents on how FBI forced it to reveal users’ data

“Tweets with booster words, such as ‘undeniable,’ and positive emotion terms, such as ‘eager’ and ‘terrific,’ were viewed as highly credible,” Mitra said.”Words indicating positive sentiment but mocking the impracticality of the event, such as ‘ha,’ ‘grins’ or ‘joking,’ were seen as less credible. So were hedge words, including ‘certain level’ and ‘suspects’,” she said.


Higher numbers of retweets also correlated with lower credibility scores. Replies and retweets with longer message lengths were thought to be more credible.”It could be that longer message lengths provide more information or reasoning, so they’re viewed as more trustworthy,” she said.

“On the other hand, a higher number of retweets, which was scored lower on credibility, might represent an attempt to elicit collective reasoning during times of crisis or uncertainty,” Mitra said. The system is not deployable yet, but the team says it could eventually become an app that displays the perceived trustworthiness of an event as it unfolds on social media.

Read More: Twitter replaces Moments with Explore tab

“When combined with other signals, such as event topics or structural information, our linguistic result could be an important building block of an automated system,” said Eric Gilbert, an assistant professor in Georgia Tech.


“Twitter is part of the problem with spreading untruthful news online. But it can also be part of the solution,” said Gilbert.

📣 Join our Telegram channel (The Indian Express) for the latest news and updates

For all the latest Technology News, download Indian Express App.

First published on: 29-01-2017 at 11:31:16 am
Latest Comment
Post Comment
Read Comments