Towards Empowering Consumers through Sentence-level Readability Scoring in German ESG Reports

TL;DR

This paper enhances sentence-level readability assessment of German ESG reports by crowdsourcing annotations, evaluating various models, and demonstrating that a fine-tuned transformer best predicts human judgments.

Contribution

It introduces a new annotated dataset for German ESG report sentences and compares multiple readability scoring methods, highlighting the effectiveness of a fine-tuned transformer model.

Findings

Native speakers find ESG report sentences generally easy to read.

Readability perception is subjective among individuals.

A fine-tuned transformer model predicts human readability with the lowest error.

Abstract

With the ever-growing urgency of sustainability in the economy and society, and the massive stream of information that comes with it, consumers need reliable access to that information. To address this need, companies began publishing so called Environmental, Social, and Governance (ESG) reports, both voluntarily and forced by law. To serve the public, these reports must be addressed not only to financial experts but also to non-expert audiences. But are they written clearly enough? In this work, we extend an existing sentence-level dataset of German ESG reports with crowdsourced readability annotations. We find that, in general, native speakers perceive sentences in ESG reports as easy to read, but also that readability is subjective. We apply various readability scoring methods and evaluate them regarding their prediction error and correlation with human rankings. Our analysis shows that, while LLM prompting has potential for distinguishing clear from hard-to-read sentences, a small finetuned transformer predicts human readability with the lowest error. Averaging predictions of multiple models can slightly improve the performance at the cost of slower inference.