|
AUTHOR(S): Ajay Babu Kakani, Sri Krishna Kireeti Nandiraju, Sandeep Kumar Chundru, Srikanth Reddy Vangala, Ram Mohan Polam, Bhavana Kamarthapu
|
TITLE Leveraging NLP and Sentiment Analysis for ML-Based Fake News Detection with Big Data |
 PDF |
ABSTRACT As a critical cybersecurity tool, Natural Language Processing (NLP) provides an automated the quick dissemination of misleading information online, necessitating the use of a fake news detecting system. The suggested fake news detection system incorporates sentiment analysis with a number of machine learning (ML) and deep learning models, such as Random Forest (RF) and Logistic Regression (LR) algorithms, Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Naive Bayes (NB), in addition to a Long Short-Term Memory (LSTM) neural network solution. The study involved extensive data preprocessing, TF-IDF, and Bag-of-Words feature extraction. The model was then evaluated using binary cross-entropy loss, accuracy and precision, recall, and F1-score assessments. Through efficient sequential and contextual text processing, the LSTM model outperformed other models in the Kaggle fake news dataset, which had over 26,000 items. In experimental evaluation, LSTM outperformed the convolutional neural network (CNN) and Extreme Gradient Boosting (XGBoost) models, achieving 95.1% accuracy, 94.4% precision, 95.3% recall, and 94.2% F1-score. LSTM deep learning (DL) algorithms demonstrate exceptional reliability in identifying deceptive content because they perform better than traditional machine learning methods, thus offering great potential as a basic cybersecurity tool to stop misinformation spread. |
KEYWORDS Fake news detection, Cybersecurity, Natural Language Processing, sentiment analysis, machine learning, LSTM, TF-IDF, Bag-of-Words |
|
Cite this paper Ajay Babu Kakani, Sri Krishna Kireeti Nandiraju, Sandeep Kumar Chundru, Srikanth Reddy Vangala, Ram Mohan Polam, Bhavana Kamarthapu. (2025) Leveraging NLP and Sentiment Analysis for ML-Based Fake News Detection with Big Data. International Journal of Computers, 10, 268-276 |
|
