Surveying the Dead Minds: Historical-Psychological Text Analysis with Contextualized Construct Representation (CCR) for Classical Chinese

TL;DR

This paper introduces a novel pipeline called CCR for analyzing historical-psychological texts in classical Chinese, leveraging transformer models and psychometric knowledge to measure psychological constructs with improved accuracy over existing methods.

Contribution

It develops the first Chinese historical psychology corpus and a contrastive learning approach, advancing computational analysis of ancient texts' psychological content.

Findings

CCR outperforms word-embedding approaches in all tasks

The pipeline exceeds GPT-4 prompting in most tasks

Validated against external data for robustness

Abstract

In this work, we develop a pipeline for historical-psychological text analysis in classical Chinese. Humans have produced texts in various languages for thousands of years; however, most of the computational literature is focused on contemporary languages and corpora. The emerging field of historical psychology relies on computational techniques to extract aspects of psychology from historical corpora using new methods developed in natural language processing (NLP). The present pipeline, called Contextualized Construct Representations (CCR), combines expert knowledge in psychometrics (i.e., psychological surveys) with text representations generated via transformer-based language models to measure psychological constructs such as traditionalism, norm strength, and collectivism in classical Chinese corpora. Considering the scarcity of available data, we propose an indirect supervised contrastive learning approach and build the first Chinese historical psychology corpus (C-HI-PSY) to fine-tune pre-trained models. We evaluate the pipeline to demonstrate its superior performance compared with other approaches. The CCR method outperforms word-embedding-based approaches across all of our tasks and exceeds prompting with GPT-4 in most tasks. Finally, we benchmark the pipeline against objective, external data to further verify its validity.