Home / Current Issue / Paper 1717884
Explainable AI-Based Fake News Detection System for Indian Online News Using Machine Learning and Deep Learning
Subject area: Science,Engineering and Technology · Area of research: Computer Science Engineering
DOI: https://doi.org/10.64388/IREV9I11-1717884
Abstract
The rapid growth of digital media and social net-working platforms has significantly increased the spread of fake news and online misinformation. Social media applications such as WhatsApp, Facebook, Instagram, and X allow information to spread rapidly among users without proper verification. In India, fake news has become a major challenge affecting politics, healthcare, education, finance, and social harmony. This paper presents an Explainable Artificial Intelligence (XAI)-based fake news detection system specifically designed for Indian online news environments. The proposed framework integrates Natural Language Processing (NLP), TF-IDF feature extraction, Multinomial Naive Bayes classification, Long Short-Term Memory (LSTM) deep learning, and Local Interpretable Model-Agnostic Explanations (LIME). Multiple datasets including Fake.csv, True.csv, IFND, Bharat-FakeNewsKosh, and Indian news headline datasets were used to improve contextual relevance for Indian misinformation detection. The system was implemented using Python, Flask, SQLite, TensorFlow, Keras, Scikit-learn, and NLTK. Experimental results demonstrate strong classification performance and improved explainability through LIME-based interpretation. The proposed framework contributes toward trust-worthy, interpretable, and practical AI-based misinformation detection systems for public awareness.
Keywords
Fake News Detection, Explainable AI, Machine Learning, Deep Learning, LSTM, LIME, TF-IDF, Naive Bayes, Flask, Indian Misinformation
How to cite this paper
@article{1717884,
author = {Roshni Priyadarshini Behera, Prof. Rakshitha B. S},
title = {Explainable AI-Based Fake News Detection System for Indian Online News Using Machine Learning and Deep Learning},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2523-2541},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717884.pdf},
abstract = {The rapid growth of digital media and social net-working platforms has significantly increased the spread of fake news and online misinformation. Social media applications such as WhatsApp, Facebook, Instagram, and X allow information to spread rapidly among users without proper verification. In India, fake news has become a major challenge affecting politics, healthcare, education, finance, and social harmony. This paper presents an Explainable Artificial Intelligence (XAI)-based fake news detection system specifically designed for Indian online news environments. The proposed framework integrates Natural Language Processing (NLP), TF-IDF feature extraction, Multinomial Naive Bayes classification, Long Short-Term Memory (LSTM) deep learning, and Local Interpretable Model-Agnostic Explanations (LIME). Multiple datasets including Fake.csv, True.csv, IFND, Bharat-FakeNewsKosh, and Indian news headline datasets were used to improve contextual relevance for Indian misinformation detection. The system was implemented using Python, Flask, SQLite, TensorFlow, Keras, Scikit-learn, and NLTK. Experimental results demonstrate strong classification performance and improved explainability through LIME-based interpretation. The proposed framework contributes toward trust-worthy, interpretable, and practical AI-based misinformation detection systems for public awareness.},
keywords = {Fake News Detection, Explainable AI, Machine Learning, Deep Learning, LSTM, LIME, TF-IDF, Naive Bayes, Flask, Indian Misinformation},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717884}
}