 GSDO: golden search dingo optimisation enabled CNN-based long short-term memory with review vectorisation for fake news detectionT.S. Steni Mol and P.S. Sreeja International Journal of Industrial and Systems Engineering, 2026, vol. 53, issue 1, 69-98 Abstract: Fake news detection is a significant chore, which not only guarantees that users deliver authentic information, but also assists in maintaining trustworthy ecosystems. Most of the present detection approaches concentrate on identifying signs from contents of news that are commonly not efficient because fake news is oftentimes purposely written to mislead users by imitating actual news. Presently, the detection of fake news is commonly classified as social context-based learning and news content-based learning. Here CNN_LSTM_GSDO, which is an efficient technique, is designed for fake news detection. Initially, input review data is fed to the review vectorisation phase. WordNet2vec and BERT are the two models utilised in the review vectorisation stage. Finally, fake news detection is performed using CNN-based LSTM, which is a transfer learning approach. It is trained by a newly devised GSDO, which is a combination of GSO and DOX. Keywords: long short-term memory; LSTM; WordNet2Vec; golden search optimisation; GSO; Dingo optimiser; DOX; convolutional neural network; CNN. (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:ids:ijisen:v:53:y:2026:i:1:p:69-98 Access Statistics for this article More articles in International Journal of Industrial and Systems Engineering from Inderscience Enterprises Ltd |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.