Treffer: A Novel Transformer-Based Deep Learning Pipeline for Multilingual Fake News Detection.

The emergence of extensive amounts of fake news on the internet made real-time fake news detection (FND) through computational tools necessary. However, the non-availability of annotated data and language-specific processing tools significantly undermines the application of FND in low-resource languages. This study introduces a transformer-based pipeline for detecting fake news and expanding annotated datasets in low-resource languages. A multilingual dataset containing 16 languages was created using machine translation. Multilingual Bidirectional Encoder Representations from Transformers (mBERT) was fine-tuned on the combined dataset and demonstrated an accuracy rate of 97% in FND. Our model could learn languageindependent features through cross-lingual language understanding (XLU) and perform similarly to monolingual models. Experiments performed on zero-shot settings indicate that our model can accurately perform FND in languages not included in the training set. To increase accessibility and practicality, the model is deployed on a Chrome web extension developed with JavaScript. The data input to the extension is collected in a dataset. Impractical data are removed using a filtering model. Overall, this study offers a novel self-expanding pipeline for FND in all languages and the expansion of annotated data in real-time, which is a significant step towards overcoming public misinformation on a global scale. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of High School Research is the property of Terra Science & Education and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)