Advancing MAISON: Integrating Deep Learning and Social Dynamics in Cyberbullying Detection and Prevention
Mehdi Ghayoumi, Kambiz Ghazinour · 2024
This paper extends the MAISON framework, introducing methodologies for detecting and preventing cyberbullying on social media platforms. At the core of our approach lies the integration of deep learning algorithms specifically designed to parse and analyze intricate data patterns. This integration elevates the accuracy and precision of cyberbullying identification, enabling the detection of both overt and subtle forms of digital harassment. Furthermore, our research delves into social dynamics, thoroughly examining user interactions and behavioral patterns. This exploration is not merely analytical but proactive, aiming to preempt cyberbullying incidents before they escalate. By using technological innovations with in-depth sociological insights, our study ventures into new territory, striving to forge a digital environment that is not only secure but also inherently supportive and empathetic. The results of our research underscore an improvement in the identification and mitigation of cyberbullying instances. These findings testify to the potential of empathetic and intelligent AI-driven solutions, which promise to revolutionize the digital communication and safety landscape.