Moral Frames in German Party Manifestos

This repository contains the annotation guidelines and human annotations for moral frames and their roles of German party manifestos (moral foundations to be added soon) of German party manifestos, as supplementary material for the NLP4DH-2025 submission "Moral reckoning: How reliable are dictionary-based methods for examining morality in text?".

Contents of this repository:

- guidelines
	- MoralFrames.pdf 

- data
	- manifestos_de
		- A1  -- annotations by coder 1
		- A2  -- annotations by coder 2
- README.md (this readme file)

Bibtex reference

@inproceedings{rehbein-etal-2025-moral,
    title = "Moral reckoning: How reliable are dictionary-based methods for examining morality in text?",
    author = "Rehbein, Ines  and
      Brauner, Lilly  and
      Ertz, Florian  and
      Reinig, Ines  and
      Ponzetto, Simone",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.nlp4dh-1.20/",
    doi = "10.18653/v1/2025.nlp4dh-1.20",
    pages = "232--250",
    ISBN = "979-8-89176-234-3",
    abstract = "Due to their availability and ease of use, dictionary-based measures of moral values are a popular tool for text-based analyses of morality that examine human attitudes and behaviour across populations and cultures. In this paper, we revisit the construct validity of different dictionary-based measures of morality in text that have been proposed in the literature. We discuss conceptual challenges for text-based measures of morality and present an annotation experiment where we create a new dataset with human annotations of moral rhetoric in German political manifestos. We compare the results of our human annotations with different measures of moral values, showing that none of them is able to capture the trends observed by trained human coders. Our findings have far-reaching implications for the application of moral dictionaries in the digital humanities."
}