Leveraging Language Models for Emotion and Behavior Analysis in Education

TL;DR

This paper introduces a non-intrusive, scalable method using large language models and prompt engineering to analyze students' emotions and behaviors from textual data, improving accuracy over traditional approaches.

Contribution

It presents a novel approach leveraging LLMs and tailored prompts for educational emotion and behavior analysis, outperforming baseline models.

Findings

Significant accuracy improvement over baselines

Effective detection of emotional and engagement states

Demonstrated scalability and practicality

Abstract

The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy concerns and scalability issues. This paper proposes a novel method leveraging large language models (LLMs) and prompt engineering to analyze textual data from students. Our approach utilizes tailored prompts to guide LLMs in detecting emotional and engagement states, providing a non-intrusive and scalable solution. We conducted experiments using Qwen, ChatGPT, Claude2, and GPT-4, comparing our method against baseline models and chain-of-thought (CoT) prompting. Results demonstrate that our method significantly outperforms the baselines in both accuracy and contextual understanding. This study highlights the potential of LLMs combined with prompt engineering to offer practical and effective tools for educational emotion and behavior analysis.