Harnessing emotions using language processing in detecting cyberbullying

Chen, Kok Chung (2025) Harnessing emotions using language processing in detecting cyberbullying. Final Year Project, UTAR.

PDF Download (2568Kb)

Abstract

Cyberbullying represents a widespread challenge across social media platforms, frequently resulting in considerable emotional and psychological distress for individuals. Although current detection systems are geared towards recognizing harmful language, they fall short in comprehensively understanding the emotional consequences of such content. This project introduces Advanced Emotion Detection, a system aimed at categorizing particular emotions and assessing their intensity within comments on social media. This project centers on Instagram, a platform characterized by visual and textual interactions that often result in cyberbullying, with the objective of refining a large language model (LLM) by utilizing data obtained from publicly available posts and comments. The final dataset collected will be processed and used to fine-tune an LLM to locate subtle expressions of emotions within text. The system will go further than the basic sentiment analysis in detecting the severity and type of emotional impact, thus allowing the correct cyberbullying incident classification. The outcome of the project is to create a fine-tuned LLM model that capable to detect and classify the severity and types of cyberbully emotional impact.

Actions (login required)