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{178095,
        author = {VEPAGUNTA GOVARDHAN KUMAR and TANI VETRI and SARVEPALLI SIVAPRIYA and PAYYAYI PRIYA and BANDI DAYAKAR},
        title = {Survey on Detecting Hate speeches in Social Media With Logistic Regression on Twitter Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2145-2148},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178095},
        abstract = {The paper addresses the challenge of detecting hate speech on social media using deep learning techniques. It proposes a novel model fusion approach that leverages a comprehensive dataset from 18 sources, consisting of 0.45 million comments. The method employs CNN and BiLSTM with an attention mechanism, specifically optimized for different subsets of the dataset. media targets individuals and groups based on demographics, making its detection a crucial yet complex task. Traditional supervised models rely on labeled datasets, but hate speech detection involves multiple aspects such as writing style and topic. This study introduces an ensemble learning approach that captures various aspects of hate speech by constructing ensembles from different perspectives Experiments conducted on five datasets in multiple languages (English, Turkish, Italian) demonstrate improved performance over baseline models. The proposed method outperforms state-of-the-art ensemble approaches in multiple scenarios, particularly improving F1-score for hate speech detection Hate speech is a growing problem that can harm individuals and communities. potential solution is using machine learning algorithms to detect and flag hate speech in text-based data This approach involves training a model on a labeled dataset containing examples classifiedas hate speech or nonhatespeech.},
        keywords = {Hate speech detection, deep learning, hate speech detection, ensemble learning Machine learning, deep learning, Hate speech, text analysis, Twitter, multinomial logistic regression},
        month = {May},
        }