Left Menu
Development News Edition

Researchers at MIT develop new ML system to combat fake news

Devdiscourse News Desk | New York | Updated: 06-10-2018 20:39 IST | Created: 06-10-2018 18:10 IST
Researchers at MIT develop new ML system to combat fake news
The researchers believe that the best approach is to focus not on the factuality of individual claims but on the news sources themselves.

To combat fake news, a team of Massachusetts Institute of Technology (MIT) researchers have developed a new Machine Learning (ML) system that helps to determine whether a news source is accurate or biased.

The researchers believe that the best approach is to focus not on the factuality of individual claims but on the news sources themselves.

"If a website has published fake news before, there's a good chance they'll do it again. By automatically scraping data about these sites, the hope is that our system can help figure out which ones are likely to do it in the first place," said lead author Ramy Baly from MIT's Computer Science and Artificial Intelligence Lab (CSAIL).

The system needs only about 150 articles to reliably detect if a news source can be trusted, suggests the study be presented at the 2018 Empirical Methods in Natural Language Processing (EMNLP) conference in Brussels.

For the study, the researchers from MIT and the Qatar Computing Research Institute (QCRI), took data from Media Bias/Fact Check (MBFC) -- a website with human fact-checkers who analyse the accuracy and biases of more than 2,000 news sites, from MSNBC and Fox News to low-traffic content farms.

The team then fed that data to an ML algorithm called a Support Vector Machine (SVM) classifier, and programmed it to classify news sites the same way as MBFC.

When given a new news outlet, the system was 65 per cent accurate at detecting whether it has a high, low or medium level of "factuality", and roughly 70 per cent accurate in detecting if it is left-leaning, right-leaning or moderate.

The team determined that the most reliable ways to detect both fake news and biased reporting were to look at the common linguistic features across the source's stories, including sentiment, complexity and structure.

For example, fake news outlets were found to be more likely to use language that is hyperbolic, subjective and emotional.

In terms of bias, left-leaning outlets were more likely to have language that related to concepts of harm/care and fairness/reciprocity, compared to other qualities such as loyalty, authority and sanctity.


TRENDING

OPINION / BLOG / INTERVIEW

Rethinking Rural Livelihoods in the Times of COVID-19

The reverse migration caused by COVID 19 pandemic has put an additional burden of about one crore people on Indian villages particularly in the states of Uttar Pradesh, Bihar, Bengal and Odisha. Besides increasing the risk of spreading the ...

‘Discounted Deaths’ and COVID 19: Anthropology of Death and Emotions

Death is a social event rather than the mere cessation of biological functions. As seen by anthropologists, death is not just physical but intensely social, cultural, and political....

Indigenous knowledge of communities a must for maximizing impact of community work

Generally, it has been observed that the majority of the academicians in higher education institutions neglect the wisdom of community people and throw their weight around thinking that they know everything and the community knows nothing. ...

In rebuking FBR, Pakistan’s courts take a stand for public health

The system, if implemented effectively, will allow Pakistans revenue service to combat the illicit trade in tobacco products and potentially add hundreds of millions of dollars to the states budget each year. ...

Videos

Latest News

UPDATE 2-German coalition parties put off decision on coronavirus stimulus package

Parties in German Chancellor Angela Merkels coalition wrestled on Tuesday over final details of a huge stimulus package to aid recovery from the COVID-19 pandemic, including whether cash incentives to buy new cars should exclude combustion ...

Lancet says concerned about validity of widely cited hydroxychloroquine study

The Lancet medical journal said on Tuesday serious scientific questions had been brought to its attention about the validity of the data behind a widely cited and already corrected study on the dangers of the use of the anti-malarial drug h...

GLOBAL MARKETS-Equities cruise to three-month highs, dollar under protest pressure

World stock markets hit their highest levels since March and oil prices jumped on Tuesday as signs of a global economic recovery from the coronavirus pandemic offset concerns over the worst civil unrest in the United States in decades. Desp...

Minnesota files civil rights charge against police over Floyd death

The state of Minnesota on Tuesday filed a civil rights charge against the Minneapolis Police Department over the death of George Floyd and said it would investigate the department to see if it engaged in systemic discriminatory practices.Mi...

Give Feedback