AgentPeerTalk: Empowering Students through Agentic-AI-Driven Discernment of Bullying and Joking in Peer Interactions in Schools

TL;DR

This paper explores how large language models, especially ChatGPT-4, can be used as agentic AI tools to help students distinguish between bullying and joking in peer interactions, aiming to improve mental health and safety.

Contribution

It introduces an agentic approach using LLMs to identify bullying in school interactions, highlighting ChatGPT-4's effectiveness and addressing challenges like bias and context limitations.

Findings

ChatGPT-4 showed the highest accuracy after agentic tuning.

LLMs' outputs are influenced by bias, political correctness, and context window size.

Agentic AI can provide real-time support to vulnerable students.

Abstract

Addressing school bullying effectively and promptly is crucial for the mental health of students. This study examined the potential of large language models (LLMs) to empower students by discerning between bullying and joking in school peer interactions. We employed ChatGPT-4, Gemini 1.5 Pro, and Claude 3 Opus, evaluating their effectiveness through human review. Our results revealed that not all LLMs were suitable for an agentic approach, with ChatGPT-4 showing the most promise. We observed variations in LLM outputs, possibly influenced by political overcorrectness, context window limitations, and pre-existing bias in their training data. ChatGPT-4 excelled in context-specific accuracy after implementing the agentic approach, highlighting its potential to provide continuous, real-time support to vulnerable students. This study underlines the significant social impact of using agentic AI in educational settings, offering a new avenue for reducing the negative consequences of bullying and enhancing student well-being.