EUVIMEDEUVIMED entdecken
Crossref

Fake News Detection Using Transfer Learning with Strategic Layer Freezing on a Fine-Tuned RoBERTa Model

Amita Jajoo, Aditya Atul Gawali, Piyush Uttamrao Patil, Niraj Pradip Tapase, Nikhil Nageshwar Domade

Multidisciplinary Journal of Research in Engineering and Technology · 20.05.2026 · 13 (1S) · 24-30

DOI: 10.65521/mjret.v13i1s.3024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Multidisciplinary Journal of Research in Engineering and Technology, online erschienen am 20.05.2026. Verfasst von Amita Jajoo und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid proliferation of misinformation across digital platforms has made automated fake news detection a critical challenge in natural language processing. This paper presents a transfer learning approach with strategic layer freezing for fake news detection, applied to a pretrained RoBERTa-based classifier. We freeze the lower six encoder layers (layers 0–5) of the pretrained model to preserve general-purpose linguistic representations, while retraining the upper six layers (layers 6–11) and the classification head on the GonzaloA/Fake News dataset comprising 40,587 labeled English-language news articles. Our approach achieves 98.19% accuracy on the held-out test set with an F1-score of 0.98, outperforming both the unmodified pretrained model (89.1%) and full fine-tuning of all layers (96.4%) by significant margins. We employ a cosine learning-rate scheduler with AdamW optimization and early stopping to prevent catastrophic forgetting of pretrained knowledge. Analysis of the confusion matrix on 2,434 test samples reveals only 44 total misclassifications (20 false negatives and 24 false positives), confirming strong performance across both classes. The fine-tuned model has been publicly deployed on the Hugging Face Hub for community use and reproducibility.

Zitieren

APA

Jajoo, A., Gawali, A. A., Patil, P. U., Tapase, N. P., & Domade, N. N. (2026). Fake News Detection Using Transfer Learning with Strategic Layer Freezing on a Fine-Tuned RoBERTa Model. Multidisciplinary Journal of Research in Engineering and Technology, 13(1S), 24-30. https://doi.org/10.65521/mjret.v13i1s.3024

Vancouver

Jajoo A, Gawali AA, Patil PU, Tapase NP, Domade NN. Fake News Detection Using Transfer Learning with Strategic Layer Freezing on a Fine-Tuned RoBERTa Model. Multidisciplinary Journal of Research in Engineering and Technology. 2026;13(1S):24-30. doi:10.65521/mjret.v13i1s.3024

BibTeX
@article{Jajoo2026,
  author = {Jajoo, Amita and Gawali, Aditya Atul and Patil, Piyush Uttamrao and Tapase, Niraj Pradip and Domade, Nikhil Nageshwar},
  title = {Fake News Detection Using Transfer Learning with Strategic Layer Freezing on a Fine-Tuned RoBERTa Model},
  journal = {Multidisciplinary Journal of Research in Engineering and Technology},
  year = {2026},
  volume = {13},
  number = {1S},
  pages = {24--30},
  doi = {10.65521/mjret.v13i1s.3024}
}
Kostenlos starten →