DIPROMATS 2023: Propaganda identification

The task aims at  finding the best techniques to identify 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. It consists on  determining whether a tweet has propaganda techniques or not.

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
URL Task
https://sites.google.com/view/dipromats2023
NLP topic
text classification
Abstract task
Classification
Dataset
DIPROMATS 2023
Year
2023
Publication link
http://journal.sepln.org/sepl…
Ranking metric
ICM

Task results

System Precision Recall F1 CEM Accuracy MacroPrecision MacroRecall MacroF1 RMSE MicroPrecision MicroRecall MicroF1 MAE MAP UAS LAS MLAS BLEX Pearson correlation Spearman correlation MeasureC BERTScore EMR Exact Match F0.5 Hierarchical F ICM MeasureC Propensity F Reliability Sensitivity Sentiment Graph F1 WAC b2 erde30 sent weighted f1
Roberta large 0.7984 0.7984 0.7984 0.7984 0.80
Xlm roberta large 0.7931 0.7931 0.7931 0.7931 0.79
Roberta base 0.7799 0.7799 0.7799 0.7799 0.78
Ixa ehu ixambert base cased 0.7796 0.7796 0.7796 0.7796 0.78
Xlm roberta base 0.7791 0.7791 0.7791 0.7791 0.78
Bert base cased 0.7763 0.7763 0.7763 0.7763 0.78
Bert base multilingual cased 0.7709 0.7709 0.7709 0.7709 0.77
Distilbert base uncased 0.7687 0.7687 0.7687 0.7687 0.77
Distilbert base multilingual cased 0.7471 0.7471 0.7471 0.7471 0.75

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.