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.

(With inputs from agencies.)


TRENDING

OPINION / BLOG / INTERVIEW

Tracking Fintech during COVID-19: Harnessing power of technology

Its abundantly clear now that as fintech cements its place in the financial sector, accelerated further by the COVID-19 pandemic, it could open the sector to new possibilities by harnessing the power of technology to deliver financial ...

Tectonic turns: How technology shaped healthcare over the decades

Tracing an episodic evolution, with technology at the interface of human and his health....

World Water Day sees crises of inequality in countries both rich and poor

... ...

Privacy and data protection: Reviewing notable policy frameworks

The evolved privacy principles and the resulting legislation across the world primarily aim to force the data collector to define the purpose for which the data is being collected along with the need to obtain explicit consent for the said ...

Videos

Latest News

Maharashtra received least vaccine doses, many vaccination centers facing closure: Aslam Shaikh

Accusing the Centre of indulging in politics, Maharashtra Cabinet Minister Aslam Shaikh on Saturday said that the state received the least number of vaccines and a majority of vaccination centres were facing closure due to shortage of doses...

Voting adjourned in Cooch Behar polling booth after 4 killed in CISF firing

Voting exercise was adjourned at a polling booth in Bengals Cooch Behar district, after four persons were killed in firing by CISF personnel in its vicinity, a senior election official said.The official also said that re-polling will be hel...

Two Christian nurses booked under blasphemy charges in Pakistan

Two Christian nurses have been booked under blasphemy charges in Pakistans Punjab province following a complaint by hospital authorities, police said, as people staged demonstrations against the duo demanding strict action against them.Acco...

Streets, markets empty as MP weekend lockdown kicks in

Streets and markets in most cities of Madhya Pradesh wore a deserted look on Saturday, uncharacteristic for the weekend, as a 60-hour lockdown started showing effect.The lockdown came into force at 6 pm on Friday.Among these places, Ratlam,...

Give Feedback