Enhancing Financial Sentiment Analysis with Expert-Designed Hint

TL;DR

This paper demonstrates that incorporating expert-designed hints, especially emphasizing numerical data, significantly enhances the performance of large language models in financial sentiment analysis, particularly for posts involving monetary information.

Contribution

Introducing expert-designed hints into LLMs to improve financial sentiment analysis, highlighting the importance of perspective-taking and numerical data understanding.

Findings

Expert-designed hints improve sentiment analysis accuracy.

Numerical data emphasis enhances performance on financial tweets.

Large language models benefit from strategic expert input.

Abstract

This paper investigates the role of expert-designed hint in enhancing sentiment analysis on financial social media posts. We explore the capability of large language models (LLMs) to empathize with writer perspectives and analyze sentiments. Our findings reveal that expert-designed hint, i.e., pointing out the importance of numbers, significantly improve performances across various LLMs, particularly in cases requiring perspective-taking skills. Further analysis on tweets containing different types of numerical data demonstrates that the inclusion of expert-designed hint leads to notable improvements in sentiment analysis performance, especially for tweets with monetary-related numbers. Our findings contribute to the ongoing discussion on the applicability of Theory of Mind in NLP and open new avenues for improving sentiment analysis in financial domains through the strategic use of expert knowledge.