Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts

TL;DR

This paper explores how prompt engineering techniques can effectively control sentiment in AI-generated texts, providing a practical alternative to fine-tuning especially when data is limited.

Contribution

It demonstrates that prompt engineering, particularly Few-Shot prompting, can reliably steer emotions in AI outputs, advancing emotion-adaptive AI development.

Findings

Prompt engineering effectively controls sentiment in LLM outputs.

Few-Shot prompting with human examples is most effective.

Prompting offers a cost-effective alternative to fine-tuning.

Abstract

The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI). However, deliberately controlling the sentiment in these systems remains challenging. The present study investigates the potential of prompt engineering for controlling sentiment in LLM-generated text, providing a resource-sensitive and accessible alternative to existing methods. Using Ekman's six basic emotions (e.g., joy, disgust), we examine various prompting techniques, including Zero-Shot and Chain-of-Thought prompting using gpt-3.5-turbo, and compare it to fine-tuning. Our results indicate that prompt engineering effectively steers emotions in AI-generated texts, offering a practical and cost-effective alternative to fine-tuning, especially in data-constrained settings. In this regard, Few-Shot prompting with human-written examples was the most effective among other techniques, likely due to the additional task-specific guidance. The findings contribute valuable insights towards developing emotion-adaptive AI systems.