Authors:
M. Rehena Sulthana, Rahul Panakkal, S. Manikandan, Muhammad Fasehullah, Andino Maseleno, S. J. Vimal Aravintha

Addresses:
School of Information Technology and Engineering, Melbourne Institute of Technology, Melbourne, Victoria, Australia. Department of Computer Science and Engineering, University of Illinois at Urbana, Champaign, Illinois, United States of America. Department of Artificial Intelligence and Machine Learning, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. College of Engineering and Technology, Southwest University, Beibei, Chongqing, China. Department of Information Systems, Institute Bakti Nusantara, Pringsewu, Lampung, Indonesia. Department of Data Science, Indiana University Bloomington, Bloomington, Indiana, United States of America.

Abstract:

Misinformation and fake news spread on digital channels, affecting public perception, social behaviour, health decisions and political and democratic processes worldwide. The growth of social media and online news sites has made it harder to tell fact from fiction. Researchers have developed an innovative Fake News Detection system using Machine Learning (ML), Deep Learning (DL), and Natural Language Processing (NLP) to automatically classify news stories as real or fake. The proposed method aims to provide a strong and efficient model that can evaluate complex linguistic patterns and contextual relationships in text. The study compares traditional machine learning algorithms, such as Naïve Bayes, Logistic Regression, SVM, and Random Forest, with advanced deep learning techniques, such as CNN, LSTM, and transformer-based models like BERT. Researchers use Bag of Words (BoW), TF-IDF, Word2Vec and contextual BERT embeddings to test their effect on classification performance. Transformer models are very effective at capturing semantic linkages in text, outperforming the standard methods in accuracy and contextual awareness by a significant margin. The easy-to-use interface lets users enter news items and receive prediction results with confidence scores, improving usability and real-world application. In this paper, Researchers discuss important ethical issues such as algorithmic bias, model interpretability, data privacy and AI deployment. This work proposes a scalable and effective AI-based approach to mitigate fake news and promote trustworthy information in the digital era. 

Keywords: Fake News Detection; Machine Learning; Deep Learning; Natural Language Processing; Text Classification; Data Pre-Processing; Feature Extraction; Supervised Learning; Binary Classification; Information Retrieval; Misinformation Detection.

Received on: 25/07/2025, Revised on: 04/10/2025, Accepted on: 21/11/2025, Published on: 09/06/2026

DOI: 10.69888/FTSIS.2026.000775

FMDB Transactions on Sustainable Intelligence and Security, 2026 Vol. 1 No. 2, Pages: 129–141

• Views : 33
• Downloads : 7

Download PDF