Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188960,
        author = {Anam Fathima and Syeda Ambareen Rana},
        title = {AN ENHANCED FAKE NEWS DETECTION SYSTEM WITH DEEP LEARNING USING NLP AND LSTM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4976-4982},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188960},
        abstract = {This research uses advances in language models to propose a novel Long Short-Term Memory (LSTM)-based network to address the complex problem of fake news detection, which has historically relied on the knowledge of professional fact-checkers due to the inherent uncertainty in fact-checking processes. By leveraging LSTM's ability to identify long-range connections in textual data, the suggested model is especially designed to handle the uncertainty present in the fake news detection problem. With an astounding accuracy of 99%, the evaluation is carried out on the reputable LIAR dataset, a well-known standard for false news identification research. Additionally, acknowledging the LIAR dataset's shortcomings, we present LIAR2 as a new benchmark that incorporates insightful information from the academic community. We establish our results as the baseline for LIAR2 by presenting comprehensive comparisons and ablation experiments on both LIAR and LIAR2 datasets. By successfully using the advantages of LSTM architecture, the suggested strategy seeks to improve our comprehension of dataset properties and aid in the development of false news detection techniques.},
        keywords = {},
        month = {December},
        }