Lisbon, Aug. 21, 2025 (Lusa) - A group of students from Lisbon's Instituto Superior Técnico (IST) has developed an Artificial Intelligence (AI) engine that aims to speed up the fact-checking process and combat disinformation, which will be presented in Montreal, Canada, on Thursday.

The model in question "seeks to reduce the time needed to evaluate content with fake news potential", speeding up fact-checking of digital content to help journalists combat the phenomenon of disinformation, the university said in a statement.

The AI system automatically carries out all the fact-checking steps done manually by professional journalists, requiring only the identification of the statement to be proven.

The user has access to all the steps taken to obtain evidence, the sources used to compile the information, and a verdict based on that information. The model also generates an article explaining the reasons for the verdict in question.

"The system was designed to increase the capacity of professional journalists and not replace them," said the system's author, Filipe Altoe, who has a PhD in computer engineering, in a statement.

For the author, the functionality constitutes "an important tool in the fight against fake news, and can reduce the virality of those that spread for several days unchallenged".

The university professor responsible for the project, Sofia Pinto, explained to Lusa that although the system "was developed and tested in English [...], it would be very interesting to develop and check how a Portuguese variant behaved".

The work involved a study with the participation of more than a hundred professional journalists to validate the functioning of the model and check the quality of the explanations generated.

The project was selected from a total of only 11 papers worldwide to be presented at the International Joint Conference on Artificial Intelligence (IJCAI), which is taking place in the Canadian city of Montreal until 22 August.

PYR/ADB // ADB.

Lusa