Researchers have developed an automated system for detecting fake news that achieved accuracy rates above 98% in tests on two datasets; in other words missing just one or two fake news items in every 100. They provide details of their approach in the International Journal of Information and Computer Security.
The new system uses a transformer encoder, an artificial intelligence (AI) model that identifies relationships between words and their context. This is combined with a deer-hunting optimisation algorithm (DHOA), a computational technique for finding effective model settings, based on modelling the way in which human hunters track and pursue prey. The researchers removed web addresses, punctuation, and common, or “stop”, words before applying their analysis to the text. The DHOA component automatically fine-tunes the model's settings rather it requiring manual selection and calibration.
Automated detection could accelerate manual fact-checking, which is often expensive and time-consuming, allowing social media platforms to screen out misleading claims quickly to avoid their rapid spread.
The next step will be to test the system on real-world social media content to see whether it can distinguish between deceptive material closely resembling legitimate reporting. As it stands, the approach is limited to text, rather than checking for the manipulation of images, deepfake videos or inconsistencies between text and visual evidence. Future work might explore how those different media types might be processed and analysed as well as looking for relationships between content and the users who post it as important clues as to whether a given item is fake news or not.
Jonnala, Y.D. and Devi, J.S. (2026) ‘Automatic fake news detection using an optimised transformer with deer hunting optimisation algorithm’, Int. J. Information and Computer Security, Vol. 31, No. 1, pp.24–48.
News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.
No comments:
Post a Comment