Unraveling Emotions with Pre-Trained Models

TL;DR

This paper evaluates fine-tuning and prompt engineering techniques for emotion recognition using transformer models and LLMs, highlighting their effectiveness and the importance of structured prompts and emotion grouping.

Contribution

It provides a comparative analysis of fine-tuning versus prompt engineering for emotion detection across different scenarios, emphasizing structured prompts and grouping techniques.

Findings

Fine-tuned models achieve over 70% accuracy in emotion recognition.

Prompt engineering and emotion grouping significantly improve LLM performance.

Structured prompts are essential for effective emotion analysis in open texts.

Abstract

Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.