Brazilian scientists have created a web platform to help people identify fake news online.
The platform was created by researchers from the Centre for Mathematical Sciences Applied to Industry (CeMEAI).
The system uses statistical methods to analyze writing characteristics, including more commonly used grammar classes.
These are then fed into a classifier based on machine learning that can distinguish fake news from real news in terms of language patterns, vocabulary and semantics.
It is then automatically derived if the content submitted on the platform is incorrect.
To get the platform to identify fake news, the researchers trained the models with a large number of databases of real and fake news. In addition, the models were exposed to the vocabulary used in over 100,000 articles published in the last five years.
According to Francisco Louzada Neto, the project coordinator and technology transfer director, the aim of the project is “to offer society an additional tool to identify, not only subjectively, whether a news item is wrong or not.”
For more information, read the original story in ZDNet.