The Moralization Corpus: Frame-Based Annotation and Analysis of Moralizing Speech Acts across Diverse Text Genres

TL;DR

This paper introduces the Moralization Corpus, a multi-genre dataset for analyzing moralizing language in argumentative texts, and evaluates LLMs' ability to detect and analyze moralizations, highlighting the complexity and subjectivity of the task.

Contribution

The paper presents a novel annotation scheme and a diverse German dataset for moralization analysis, along with an evaluation of LLM performance and challenges in automatic moralization detection.

Findings

Detailed prompts improve LLM performance more than few-shot methods.

Moralization detection is highly subjective and context-dependent.

The corpus enables cross-genre analysis of moral language.

Abstract

Moralizations - arguments that invoke moral values to justify demands or positions - are a yet underexplored form of persuasive communication. We present the Moralization Corpus, a novel multi-genre dataset designed to analyze how moral values are strategically used in argumentative discourse. Moralizations are pragmatically complex and often implicit, posing significant challenges for both human annotators and NLP systems. We develop a frame-based annotation scheme that captures the constitutive elements of moralizations - moral values, demands, and discourse protagonists - and apply it to a diverse set of German texts, including political debates, news articles, and online discussions. The corpus enables fine-grained analysis of moralizing language across communicative formats and domains. We further evaluate several large language models (LLMs) under varied prompting conditions for the task of moralization detection and moralization component extraction and compare it to human annotations in order to investigate the challenges of automatic and manual analysis of moralizations. Results show that detailed prompt instructions has a greater effect than few-shot or explanation-based prompting, and that moralization remains a highly subjective and context-sensitive task. We release all data, annotation guidelines, and code to foster future interdisciplinary research on moral discourse and moral reasoning in NLP.