An Algorithm-based fake news detector to fight against misinformation

Aug 21, 2018, 6:45 pm

Moupiya D.

More Post

Researchers at the University of Michigan have developed a fake news detector to help fight against misinformation. The Michigan researchers who have developed the detector found out that in comparison to humans it sometimes works better at correctly identifying fake news stories.

It is an algorithm-based system that identifies telltale linguistic cues in fake news stories. – The University of Michigan Team

The Fake news detector has been tested and it is found to be successful up to 76 percent of the time as compared to the human rate which is approx 70 percent. The linguistic analysis could also be studied to identify fake news article that is too new to be cross-checked with other facts or stories.

An automated solution could be an important tool for sites that are struggling to deal with an onslaught of fake news stories, often created to generate clicks or to manipulate public opinion. – Rada Mihalcea, the U-M computer science and engineering professor.

It is a real deal to find out the fake story and hence social media sites rely heavily on human editors. And most of the time before the news could be verified and proved to be fake the damage has been already done.

According to Mihalcea “You can imagine any number of applications for this on the front or back end of a news or social media site.” Fake news detector Algorithms analyzing written speech are quite common nowadays as claimed by Mihalcea and the real challenge in building a fake news detector is not in building the algorithm itself, but in finding the right data with which to train that algorithm.

Ultimately Mihalcea has created its own data to develop a fake news detector for those individuals who quickly write the fake news in return for a monetary reward. But finally, the Michigan teams turned the algorithms to a dataset, resulting in a 76 percent success rate.

Brand Partnership
Your brand needs a brand voice. Contact our marketing team for brand partnership with us.
Talk to Us
Join our Newsletter
Sign up to receive top tech stories daily delivered in your inbox
Share your thoughts. Enable the box to comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.