- PM Modi visit USAOnly the mirror in my washroom and phone gallery see the crazy me : Sara KhanKarnataka rain fury: Photos of flooded streets, uprooted treesCannes 2022: Deepika Padukone stuns at the French Riviera in Sabyasachi outfitRanbir Kapoor And Alia Bhatt's Wedding Pics - Sealed With A KissOscars 2022: Every Academy Award WinnerShane Warne (1969-2022): Australian cricket legend's life in picturesPhotos: What Russia's invasion of Ukraine looks like on the groundLata Mangeshkar (1929-2022): A pictorial tribute to the 'Nightingale of India'PM Modi unveils 216-feet tall Statue of Equality in Hyderabad (PHOTOS)
Indian men's hockey team captain Harmanpreet Singh has been named Player of the Year 2024
- World Boxing medallist Gaurav Bidhuri to flag off 'Delhi Against Drugs' movement on Nov 17
- U23 World Wrestling Championship: Chirag Chikkara wins gold as India end campaign with nine medals
- FIFA president Infantino confirms at least 9 African teams for the 2026 World Cup
- Hockey, cricket, wrestling, badminton, squash axed from 2026 CWG in Glasgow
- FIFA : Over 100 female footballers urge FIFA to reconsider partnership with Saudi oil giant
How to make your tweet credible Last Updated : 28 Jan 2017 05:33:25 PM IST (File Photo)
An India-origin researcher has put together a system that would help analyse whether your tweet is credible or not, a report said.
A team led by Georgia Tech Ph.D. candidate Tanushree Mitra scanned 66 million tweets linked to nearly 1,400 real-world events to build a language model that identified words and phrases that lead to strong or weak perceived levels of credibility on Twitter.
"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," Mitra said in a statement.
The team looked at tweets surrounding 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.
The team asked people to judge the posts on their credibility -- from "certainly accurate" to "certainly inaccurate" -- and then fed the words into a model that split them into 15 different linguistic categories.
The Georgia Tech computer 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's significantly higher than the random baseline of 25 per cent, the research said.
"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 added.
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," she added.
The system, when deployed, could eventually become an app that displays the perceived trustworthiness of an event as it unfolds on social media.IANS For Latest Updates Please-
Join us on
Follow us on
172.31.16.186