# Wage Sentiment Indices Derived from Survey Comments via Large Language Models

## TL;DR

This paper introduces a novel Wage Sentiment Index derived from survey comments using Large Language Models, which effectively forecasts wage trends in Japan and outperforms existing models.

## Contribution

It develops a new LLM-based sentiment index specifically for wages, extending previous sentiment frameworks and creating a scalable architecture for integrating diverse data sources.

## Key findings

- WSI models outperform baseline approaches
- LLM-based indices improve forecasting accuracy
- Potential to enhance economic policy responsiveness

## Abstract

The emergence of generative Artificial Intelligence (AI) has created new opportunities for economic text analysis. This study proposes a Wage Sentiment Index (WSI) constructed with Large Language Models (LLMs) to forecast wage dynamics in Japan. The analysis is based on the Economy Watchers Survey (EWS), a monthly survey conducted by the Cabinet Office of Japan that captures real-time economic assessments from workers in industries highly sensitive to business conditions. The WSI extends the framework of the Price Sentiment Index (PSI) used in prior studies, adapting it specifically to wage related sentiment. To ensure scalability and adaptability, a data architecture is also developed that enables integration of additional sources such as newspapers and social media. Experimental results demonstrate that WSI models based on LLMs significantly outperform both baseline approaches and pretrained models. These findings highlight the potential of LLM-driven sentiment indices to enhance the timeliness and effectiveness of economic policy design by governments and central banks.