The task aims at finding the best techniques to identify and categorize propagandistic tweets from governmental and diplomatic sources on a dataset of tweets in English, posted by authorities of China, Russia, United States and the European Union. The task consists on categorising propagandistic tweets in 15 propagandistic techniques.
Publication
Pablo Moral, Guillermo Marco, Julio Gonzalo, Jorge Carrillo-de-Albornoz, Iván Gonzalo-Verdugo (2023) Overview of DIPROMATS 2023: automatic detection and characterization of propaganda techniques in messages from diplomats and authorities of world powers. Procesamiento del Lenguaje Natural, Revista nº 71, septiembre de 2023, pp. 397-407.
Language
English
NLP topic
Abstract task
Dataset
Year
2023
Publication link
Ranking metric
ICM
Task results
| System | ICM Norm Sort ascending |
|---|---|
| Roberta large | 0.5526 |
| Mistral-7B-v03 | 0.5384 |
| Qwen2.5-7B | 0.5382 |
| Llama-3.1-8B | 0.5331 |
| Xlm roberta large | 0.5123 |
| Roberta base | 0.4406 |
| Bert base cased | 0.4271 |
| Ixa ehu ixambert base cased | 0.4004 |
| Bert base multilingual cased | 0.3884 |
| Xlm roberta base | 0.3773 |
