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{167093,
        author = {Uvaiskhan and BalaMurugan and Sabari Ramachandran},
        title = {Real Time Spam Mail  Deracination Expert System using NLP and Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {468-472},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167093},
        abstract = {Email has become an integral part of communication in today's world, playing a crucial role in both personal and professional domains. It provides a quick and convenient way to exchange information, documents, and messages globally. The surge in cybersecurity incidents has witnessed attackers increasingly exploiting sophisticated spam emails as a gateway to breach government systems, major corporations, and the online platforms of public figures and organizations worldwide. While the public eye is keenly focused on detecting spam within vast email datasets, the challenge has escalated due to the growing complexity of camouflage techniques employed by cybercriminals. Existing detection methods struggle to keep pace with the intricate deception methods and the sheer volume of emails, emphasizing the urgent need for innovative and adaptive approaches, including advanced machine learning, behavioural analysis, and collaborative threat intelligence sharing, to fortify our defences against evolving cyber threats. In this project, we proposed to design a novel efficient approach named E-Mail Screener for big e-mail data classification into four different classes: Normal, Fraudulent, Harassment, and Suspicious E-mails by using NLP and BiLSTM. The new method includes two important stages, sample expansion stage and testing stage under sufficient samples. This project The NLP and BiLSTM efficiently captures meaningful information from E-mails that can be used for forensic analysis as evidence. Experimental results revealed that E-Mail Screener performed better than existing ML algorithms and achieved a classification accuracy of 99.1% using the novel technique of BiLSTM with recurrent gradient units. As different types of topics are discussed in E-mail content analysis. E-Mail Screener effectively outperforms existing methods while keeping the classification process robust and reliable.},
        keywords = {E-Mail Screener, NLP and BiLSTM.},
        month = {August},
        }