Assessing the Relevance of Categories of Annotated Text to Identify and Measure Persuasion Techniques

Miguel Fernández; Marcelo Santos; Andrea Riquelme; Matías Vogel; Marcelo Mendoza

doi:10.2991/978-94-6463-868-4_23

<Previous Article In Volume

Next Article In Volume>

Assessing the Relevance of Categories of Annotated Text to Identify and Measure Persuasion Techniques

Authors

Miguel Fernández¹, Marcelo Santos², Andrea Riquelme³, Matías Vogel², Marcelo Mendoza¹^{, *}

¹School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile

²School of Communication, Universidad Diego Portales, Santiago, Chile

³School of Political Sciences and Public Administration, Universidad de Talca, Talca, Chile

^*Corresponding author. Email: mafernandez17@uc.cl

Corresponding Author

Marcelo Mendoza

Available Online 22 October 2025.

DOI: 10.2991/978-94-6463-868-4_23 How to use a DOI?
Keywords: Propaganda; Persuasion Techniques; Natural Language Processing (NLP)
Abstract: Natural Language Processing (NLP) techniques to detect propaganda are a field in development. Though many works point towards ‘counting’ the persuasion techniques, less attention is dedicated to the actual relevance, beyond frequency. We introduce an operationalization of relevance as the combination of frequency and harm. To assess it the research employs a sequential mixed methods approach, composed by: a 200-respondents survey on perceived frequency and level of harm of propaganda techniques; a comparative analysis of previous works on computational text-analysis of propaganda; and 4 focus groups with academic and practitioner experts in the fields of communications, political science, sociology, computational sciences and other similar areas that deal with propaganda, misinformation, fact-checking and so on. The results point to a handful of techniques with little relevance, while offers a selection of the most relevant persuasion techniques that allow for more parsimonious use of computational efforts in propaganda detection.
Copyright: © 2025 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the International Conference on Communication and Applied Technologies 2025 (ICOMTA 2025)
Series: Atlantis Highlights in Social Sciences, Education and Humanities
Publication Date: 22 October 2025
ISBN: 978-94-6463-868-4
ISSN: 2667-128X
DOI: 10.2991/978-94-6463-868-4_23 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Miguel Fernández
AU  - Marcelo Santos
AU  - Andrea Riquelme
AU  - Matías Vogel
AU  - Marcelo Mendoza
PY  - 2025
DA  - 2025/10/22
TI  - Assessing the Relevance of Categories of Annotated Text to Identify and Measure Persuasion Techniques
BT  - Proceedings of the International Conference on Communication and Applied Technologies 2025 (ICOMTA 2025)
PB  - Atlantis Press
SP  - 241
EP  - 253
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-868-4_23
DO  - 10.2991/978-94-6463-868-4_23
ID  - Fernández2025
ER  -

download .riscopy to clipboard