Researchers at University of Michigan have developed a fake news detector to help fight against misinformation.
The technology is "an algorithm-based system that identifies telltale linguistic cues in fake news stories." The team says the system is "comparable to and sometimes better than humans at correctly identifying fake news stories."
According to their study, linguistic analysis tracks things like grammatical structure, word choice, punctuation and complexity.
But there are challenges to making sure the system properly deciphers stories.
Researchers say the difficulty in building a fake news detectors is not in developing the algorithm itself, "but in finding the right data with which to train that algorithm."
The system is still in its beta stage. Details of the fake news detector system will be presented on August 24 at the International Conference on Computational Linguistics in Santa Fe.
Read the full study here.
