Explainable AI (XAI) for Spam Detection: The “Lens” Approach

Author(s)	Mr. Raghul Sachin R, Mr. Arun Karthik V, Prof. Dr. Niveditha S
Country	India
Abstract	This paper presents a methodology for transparent spam detection based on the use of a Random Forest classifier and Explainable Artificial Intelligence (XAI). We first confirm the classifier’s high predictive accuracy and then address the issue of black-box opacity by implementing Local Interpretable Model-agnostic Explanations (LIME) for semantic and contextual transparency. Our method highlights the major issue of false positives, which is quite challenging in the case of machine learning models. Our framework starts by training a Random Forest to identify the raveled textual distribution of a standard SMS and email spam dataset, balanced via SMOTE. The heart of our self-adaptive method is a Human-in-the-Loop (HITL) override feature within this transparent decision space. Giving the models reasoning, which identifies the precise linguistic cues leading to a spam prediction, helps to find the best context specific whitelist rule. This way misclassified emails are not only saved but the filter also gets refined, hence, this is a great use of explainable models for real, reliable cybersecurity.
Keywords	Explainable AI, LIME, Spam Detection, Human-in-the-Loop, Random Forest, Cybersecurity
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-08

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research