Technology Inceptions: NASA's Chandra X-ray Observatory back in action  |  Science Innovations: GenNext Solar Cells with Record-breaking efficiency invented  |  Science Innovations: Canadian researchers develop world’s fastest camera   |  Science Innovations: Scientists discover “ultra-stripped supernova”, the origin of gold and platinum   |  Parent Interventions: Why do bees stop buzzing during a total solar eclipse?   |  Parent Interventions: Lie detection is not an easy task  |  Teacher Insights: Can we learn while sleeping?  |  Teacher Insights: Sitting up straight boosts math performance  |  Science Innovations: Engineers design molecules that store thermal energy   |  Technology Inceptions: Russia May Bring Forward Manned Launch After Rocket Failure  |  Technology Inceptions: New Nokia Smartphone's India Launch Expected Today, how to Watch Live Stream  |  Science Innovations: Kahne Lab prepares to combat superbugs   |  Teacher Insights: False beliefs die hard  |  Science Innovations: New wayto convert metals to superconductors  |  Technology Inceptions: Willmott Dixon Trials 'Bionic' Vest  |  
  • Pallikkutam Magazine
  • Companion Magazine
  • Mentor
  • Smart Board

October 04, 2018 Thursday 04:53:45 PM IST
MIT develops a new method to detect fake news

Fact-checking has landed in a deep crisis with the rise of social media. The traditional tools in the sites like Politifact and Snopes have proven too slow that by the time they've gotten through verifying or debunking a fact, there's a good chance it's already traveled across the globe and back again.

Social media companies are also struggling to control fake news. Facebook plans to have 20,000 human moderators by the end of the year, and is spending many millions developing its own fake-news-detecting algorithms.

MIT Researchers have developed a new method of detecting fake news by focusing not on the factuality of individual claims, but on the news sources themselves. Using this tack, they've demonstrated a new system that uses machine learning to determine if a source is accurate or politically biased.They are preparing to present their study in the 2018 Empirical Methods in Natural Language Processing (EMNLP) conference in Brussels, Belgium.

"If a website has published fake news before, there's a good chance they'll do it again," says postdoctoral associate RamyBaly, lead author on a new paper about the system. "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."

Shoot down the source is the new target of fake news annihilation strategy! The researchers propose to use the machine learning algorithms to make identification of sources of fake news easier.

Source: http://news.mit.edu/2018/mit-csail-machine-learning-system-detects-fake-news-from-source-1004

Comments