Multimodal Cyberbullying Detection In Videos

The rise of social media alongside the Internet has significantly expanded, becoming the dominant networking platform in the 21<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> century. However, while fostering social connections, it also engenders negative consequences such as online abuse, harassment, cyberbullying, cybercrime, and trolling. Particularly concerning is cyberbullying, which often results in severe mental and physical anguish, especially for women and children, sometimes leading to suicide attempts. Online harassment is another issue of significant societal concern, involving the dissemination of private conversations, rumors, and sexual remarks. Consequently, identifying bullying language or messages on social media has become a priority for researchers. This work aims to devise an effective method for detecting online abusive and bullying messages by integrating natural language processing and machine learning techniques.