Data Analytics System for Offensive Memes Text Classification in Social Network

Sentiment analysis has evolved as a pivotal element of understanding mortal feelings and opinions in the digital period. Memes, as a popular form of online communication, frequently synopsize sentiments in a visually engaging manner. In the realm of online communication, the frequence of multi-modal content, particularly memes combining textbook and images, has raised enterprises regarding the dispersion of obnoxious or dangerous material. This exploration proposes a new approach grounded on deep literacy ways for the bracket of obnoxious memes in multi- modal data sets to address this issue. The vital task involves the comprehensive analysis of both textual and visual factors to directly identify and classify unhappy content. We're proposing a new approach in this study. sentiment analysis from meme images using Optical Character Recognition (OCR) technology with Deep literacy algorithms for textbook bracket and image bracket using Conventional neural network algorithm. Our approach involves rooting textbook content from meme images using OCR, enabling the analysis of textual rudiments to infer sentiments. Through this innovative approach, we aim to enhance analysis capabilities in the visual content using pretrained Conventional neural network model. The proposed methodology demonstrates promising results, slipping light on the eventuality for OCR driven VADER sentiment analysis and Pretrained CNN to classify the nuanced feelings bedded in meme culture and contribute to a further comprehensive understanding of online sentiment dynamics

Analytics · Data science · Information retrieval · Offensive · Social media · Social network analysis · World Wide Web · Advanced Malware Detection Techniques · Computer Science · Engineering · Hate Speech and Cyberbullying Detection · Spam and Phishing Detection