Detection of Cyberbullying on Social Media Using Machine learning

Machine Learning

Cyberbullying represents a significant challenge in the online realm, impacting both teenagers and adults and giving rise to severe consequences such as suicide and depression. The imperative for regulating content on social media platforms has become increasingly evident. In response to the incidents of harm caused by cyberbullying, we employ data sourced from two distinct manifestations of this phenomenon: hate speech tweets on Twitter. Our objective is to construct a model utilizing the Support Vector Machine (SVM) algorithm in the field of machine learning to detect instances of cyberbullying within textual data. The pervasive nature of cyberbullying has necessitated a proactive approach to mitigate its adverse effects on individuals, particularly the vulnerable demographic of teenagers. The alarming rise in incidents resulting in tragic outcomes like suicide and depression underscores the urgency of addressing this issue. Recognizing the role of social media platforms as conduits for cyberbullying, there is a compelling need for effective content regulation to create a safer online environment. To tackle this challenge, we leverage data derived from hate speech tweets on the Twitter platform, representing two distinct forms of cyberbullying. Employing the Support Vector Machine (SVM) algorithm within the realm of machine learning, we aim to develop a robust model capable of identifying cyberbullying instances embedded in textual data. This approach reflects a proactive stance in combating the detrimental impacts of cyberbullying, emphasizing the role of technological interventions and algorithmic solutions in fostering a more secure and supportive online space. In addition, continuous monitoring and adaptation of the model will be crucial to staying ahead of evolving cyberbullying tactics and safeguarding the well-being of internet users.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.