Overview of DIPROMATS 2023: automatic detection and characterization of propaganda techniques in messages from diplomats and authorities of world powers
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/137203
Title: | Overview of DIPROMATS 2023: automatic detection and characterization of propaganda techniques in messages from diplomats and authorities of world powers |
---|---|
Other Titles: | Overview de DIPROMATS 2023: detección y caracterización automáticas de técnicas de propaganda en mensajes de diplomáticos y autoridades de potencias mundiales |
Authors: | Moral, Pablo | Marco Remón, Guillermo | Gonzalo Arroyo, Julio | Carrillo-de-Albornoz, Jorge | Gonzalo-Verdugo, Iván |
Keywords: | Propaganda | Digital Diplomacy | Twitter | Information Contrast Model | Diplomacia digital | Modelo de Contraste de Información |
Issue Date: | Sep-2023 |
Publisher: | Sociedad Española para el Procesamiento del Lenguaje Natural |
Citation: | Procesamiento del Lenguaje Natural. 2023, 71: 397-407. https://doi.org/10.26342/2023-71-31 |
Abstract: | This paper presents the results of the DIPROMATS 2023 challenge, a shared task included at the Iberian Languages Evaluation Forum (IberLEF). DIPROMATS 2023 provides a dataset with 12012 annotated tweets in English and 9501 tweets in Spanish, posted by authorities of China, Russia, United States and the European Union. Three tasks are proposed for each language. The first one aims to distinguish if a tweet has propaganda techniques or not. The second task seeks to classify the tweet into four clusters of propaganda techniques, whereas the third one offers a fine-grained categorization of 15 techniques. For the three tasks we have received a total of 34 runs from 9 different teams. | Este artículo presenta los resultados de DIPROMATS 2023, una tarea compartida incluida en el Iberian Languages Evaluation Forum (IberLEF). DIPROMATS 2023 proporciona un conjunto de datos con 12.012 tweets anotados en inglés y 9.501 tweets en español, publicados por autoridades de China, Rusia, Estados Unidos y la Unión Europea. Se proponen tres tareas para cada idioma. La primera tiene como objetivo distinguir si un tweet tiene técnicas de propaganda o no. La segunda tarea busca clasificar el tweet en cuatro grupos de técnicas de propaganda, mientras que la tercera ofrece una categorización detallada de 15 técnicas. Para las tres tareas, hemos recibido un total de 34 ejecuciones de 9 equipos diferentes. |
Sponsor: | This work was partially supported by the Spanish Ministry of Science and Innovation under the projects “FairTransNLP: Midiendo y Cuantificando el sesgo y la justicia en sistemas de PLN”(PID2021-124361OB-C32), and “Desinformación y agresividad en Social Media: bias, controversia y veracidad” (PGC2018-096212-B-C32). This work has also been partially financed by the European Union (NextGenerationEU funds) through the “Plan de Recuperación, Transformación y Resiliencia”, by the Ministry of Economic Affairs and Digital Transformation and by UNED. Guillermo Marco is supported by the Spanish Ministry of Science and Innovation under the grant FPU20/07321 and he is also a postgraduate fellow of the City Council of Madrid at the Residencia de Estudiantes (2022–2023). |
URI: | http://hdl.handle.net/10045/137203 |
ISSN: | 1135-5948 |
DOI: | 10.26342/2023-71-31 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © Sociedad Española para el Procesamiento del Lenguaje Natural. Distribuido bajo Licencia Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 |
Peer Review: | si |
Publisher version: | https://doi.org/10.26342/2023-71-31 |
Appears in Collections: | Procesamiento del Lenguaje Natural - Nº 71 (2023) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
![]() | 1,04 MB | Adobe PDF | Open Preview | |
This item is licensed under a Creative Commons License