CultureBERT: Measuring Corporate Culture With Transformer-Based Language Models

TL;DR

This paper develops transformer-based language models to measure corporate culture from employee reviews, outperforming traditional methods and providing a new tool for analyzing organizational values and environment.

Contribution

It introduces a novel dataset of employee reviews labeled for corporate culture and fine-tunes transformer models to improve classification accuracy over traditional approaches.

Findings

Transformer models classify reviews 17-30% more accurately.

Models outperform traditional text classification methods.

Publicly available models facilitate future research.

Abstract

This paper introduces transformer-based language models to the literature measuring corporate culture from text documents. We compile a unique data set of employee reviews that were labeled by human evaluators with respect to the information the reviews reveal about the firms' corporate culture. Using this data set, we fine-tune state-of-the-art transformer-based language models to perform the same classification task. In out-of-sample predictions, our language models classify 17 to 30 percentage points more of employee reviews in line with human evaluators than traditional approaches of text classification. We make our models publicly available.