Hybrid AI-Based Hate Speech Detection on Social Media Using NLP and Deep Learning

Author(s)	Mr. Sachin Sanjay Warude, Ms. Sakshi Vilas Shinde, Ms. Mrunal Devidas Patil, Ms. Isha Jagdish Patil, Mr. Kalpesh Sunil Pawar
Country	India
Abstract	The rapid growth of social media has increased the spread of hate speech, cyberbullying, and offensive content, making manual moderation difficult. This project proposes SafeSocial AI, a hybrid hate speech detection system that uses Natural Language Processing (NLP), Machine Learning, and Deep Learning techniques to analyze both text and image-based content. TF-IDF with Support Vector Machine (SVM) and Logistic Regression models is used for text classification, while a Convolutional Neural Network (CNN) is used for image-based hate detection. The system classifies content as hate or neutral and provides intelligent moderation features such as toxicity analysis, hate-word highlighting, safe reply generation, and text sanitization. The platform is developed using Flask, HTML, CSS, JavaScript, and SQLite database integration. Experimental results show that the proposed system can effectively detect harmful social media content and help create safer online communities.
Keywords	Hate Speech Detection, Natural Language Processing, Machine Learning, Deep Learning CNN, TF-IDF, Content Moderation, Social Media Analytics, Cyberbullying.
Field	Engineering
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-14

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