Social Media Cyberbullying Detection Applying Machine Learning
N Anuharini, C R Devadharshini, S. Sowmiya, S Pavithra · 2025
Cyberbullying on social media platforms has grown to be a pervasive and concerning issue that has an influence on individual’s general state of wellness and psychological health globally. This paper suggests a cyberbullying detection system that makes use of the Support Vector Machine (SVM) algorithm in order to tackle this issue. The technology seeks to automatically detect and highlight instances of cyberbullying in real-time social media material by utilizing machine learning. The first step in creating the detection system is gathering and classifying a large dataset of posts and comments that include instances of both cyberbullying and non-cyberbullying. The bag-of-words or TF-IDF approaches are employed to extract significant characteristics from the text data after it has been pre-processed by eliminating unnecessary information, tokenizing it, and changing the text to lowercase. The SVM classifier, which looks for the best hyper plane to efficiently separate cyberbullying from non-cyberbullying information, is trained using these converted feature vectors as inputs. With a fresh test dataset, measures like ROC-AUC, precision, F1-score, recall, and accuracy are examined to see how well the SVM model detects instances of cyberbullying. Model fine-tuning is accomplished by experimenting with various SVM hyperparameters and cross-validation techniques in order to enhance the system’s performance.