Refined and Segmented Price Sentiment Indices from Survey Comments

TL;DR

This paper develops refined price sentiment indices from survey comments by classifying comments using large language models, enabling more accurate and specific insights into price trends from both consumer and business perspectives.

Contribution

It introduces a method to classify survey comments with LLMs to create more precise and segmented price sentiment indices, improving correlation with existing indices.

Findings

Enhanced classification accuracy of price-related comments using LLMs.

Construction of more specific and higher-correlation price sentiment indices.

Integration of multiple LLM outputs improves classification performance.

Abstract

We aim to enhance a price sentiment index and to more precisely understand price trends from the perspective of not only consumers but also businesses. We extract comments related to prices from the Economy Watchers Survey conducted by the Cabinet Office of Japan and classify price trends using a large language model (LLM). We classify whether the survey sample reflects the perspective of consumers or businesses, and whether the comments pertain to goods or services by utilizing information on the fields of comments and the industries of respondents included in the Economy Watchers Survey. From these classified price-related comments, we construct price sentiment indices not only for a general purpose but also for more specific objectives by combining perspectives on consumers and prices, as well as goods and services. It becomes possible to achieve a more accurate classification of price directions by employing a LLM for classification. Furthermore, integrating the outputs of multiple LLMs suggests the potential for the better performance of the classification. The use of more accurately classified comments allows for the construction of an index with a higher correlation to existing indices than previous studies. We demonstrate that the correlation of the price index for consumers, which has a larger sample size, is further enhanced by selecting comments for aggregation based on the industry of the survey respondents.