Copyright © 2025 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{169666,
        author = {KATROTH BALAKRISHNA MARUTHIRAM and GUJJE VIJAYAKRISHNA},
        title = {TACKLING CYBER HATRED WITH MACHINE LEARNING AND FUZZY LOGIC},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {2034-2042},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169666},
        abstract = {The project centers on addressing the concerning issue of cyber-hate, which has significantly escalated with the widespread adoption of social media platforms. It acknowledges the urgency and importance of dealing with this problem within the digital landscape. To combat cyber-hate, the project proposes the use of various machine learning and deep learning techniques. These include Naive Bayes, Logistic Regression, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Each of these methods likely serves a specific purpose in identifying, classifying, or analyzing patterns within hate speech or offensive content. The project implements two classifiers on hate speech data and enhances their performance using optimization methods such as Particle Swarm Optimization and Genetic Algorithms. These optimization techniques are likely employed to fine-tune the classifiers and improve their accuracy in detecting cyber-hate instances. Additionally, the inclusion of Fuzzy Logic aims to enhance the comprehension of text data, accounting for its inherent complexity and nuances. The primary goal is to develop a more effective and realistic approach to cyber-hate detection. This involves incorporating a critical thinking perspective, which likely means considering contextual cues and subtle nuances beyond explicit keywords or phrases. Furthermore, the utilization of optimization techniques and fuzzy logic-based systems is aimed at creating a more nuanced understanding of hate speech, making the detection process more accurate and aligned with real-world complexities. The project extends its capabilities through the integration of advanced ensemble techniques, specifically a Voting Classifier and a Stacking Classifier. The Stacking Classifier achieves an impressive 100% accuracy, demonstrating its robustness in identifying cyber hate instances. Leveraging these ensemble models enhances the overall effectiveness of the cyber-hate detection system.},
        keywords = {Cyberbullying, fuzzy logic, logistic regression, multinomial Naive Bayes, PSO, VADER.},
        month = {November},
        }