Search

Cyberbullying is a major social problem that has been affecting people across the globe. With the rise of social media platforms, cyberbullying has become even more prevalent, making it necessary to develop tools that can effectivelydetect cyberbullying and prevent its negative impact on individuals and society. Cyberbullying victims are known to become dangerously afraid as a result, and they may even have suicide or violent retaliation ideas. They experience anxiety, depression, and low self-esteem. Because it occurs, "behind the scenes" and "24/7" cyberbullying is worse than physical bullying. Bullying tweets or comments persist for a long time and continue to affect the victim's mental health negatively. It resembles ragging in many ways, with the exception that it takes place in front of thousands of shared friends and that the wounds endure as long as the online messages do. The humiliating and upsetting text causes the victims unimaginable amounts of embarrassment. The effects are significant and even worse. Nine out of ten times, or in the majority of cases, teenage victims do not tell their guardians or parents out of embarrassment and go into despair or,in the worst circumstances, commit suicide. To precisely identify cyberbullying in tweets, we have applied several machines learning techniques, including multinomial NB, SVM, logistic regression, decision tree classifier, and SGD classifier. By utilizing these algorithms, we have been able to identify cyberbullying with a high degree of accuracy, allowing us to stop it in its tracks and lessen its damaging effects. Furthermore, we have also developed a web application that allows users to check whether a tweet is cyberbullying or not and it also tells which category the tweet falls under like religion, gender, ethnicity, and age. The web application provides a simple and user-friendly interface thatallows users to easily check whether their tweets are considered cyberbullying or not. Overall, this research paper presents a comprehensive approach to detecting cyberbullying on Twitter using machine learning techniques. Our results demonstrate the effectiveness of these techniques in detecting cyberbullying and highlight the potential of these techniques for preventing the negative impact of cyberbullying on individuals and society. [ABSTRACT FROM AUTHOR]

We describe an accurate and scalable method for face clustering. A group of faces is classified based on their prospective identities. The task is presented as a link prediction problem, where two faces are linked if they have the same identity. The fundamental premise is that the local context in the feature space surrounding an instance (facial) contains crucial knowledge about the interconnectedness of this occurrence with its neighbors. The key contribution of this work is at the beginning the face is detected using the computer vision-based detection algorithm and extracted the features using VGG16 the pre-trained model. By applying the Euclidian distance algorithm, the similarity score of the face is obtained. Finally, similar faces are clustered using unsupervised learning algorithms such as K-means and Density-Based Spatial Clustering of Applications with Noise(DBSCAN). Furthermore, these two clusters are compared and DBSCAN gives a better silhouette score for DBSCAN than the K-means score. [ABSTRACT FROM AUTHOR]