A New Approach to Textual Analysis using Large Language Models: Application to the Analysis of Recent Wage and Price Developments in Japan
IZAWA Kimihiko, KAMEI Ikuo, SHIBATA Nao, TAKAHASHI Yusuke, YONEYAMA Shunichi
Research and Statistics Department
Abstract
This paper examines whether textual data analysis using Large Language Models (LLMs) can be applied to assessing economic activity and prices in light of the rapid development of LLMs in recent years. LLMs have advantages in that there are a wide range of models available for use without large initial costs and that these models, which have already acquired basic knowledge of language, can analyze any topic or text and are beginning to be used in economic analysis more widely, including those of central banks. This paper, as an example, attempts to use LLMs to analyze recent wage and price developments in Japan using comments from the Cabinet Office's Economy Watchers Survey. The results suggest that the cause of increasing selling prices is gradually shifting from raw material costs to labor costs.
Notice
The Bank of Japan Review Series is published by the Bank to explain recent economic and financial topics for a wide range of readers. This report, 2025-E-5, is a translation of the Japanese original, 2024-J-14, published in December 2024. Views expressed are those of the authors and do not necessarily reflect those of the Bank. If you have any comments or questions, please contact Research and Statistics Department (E-mail: post.rsd22@boj.or.jp). The Bank of Japan Review Series and the Bank of Japan Working Paper Series are available at https://www.boj.or.jp/en/index.htm.
First, please LoginComment After ~