Exploración de metavariables para la clasificación de la persuasión en textos de memes políticos
DOI:
https://doi.org/10.5753/reic.2026.6962Keywords:
metavariables, persuasión, clasificación de memes, clasificación de textos cortos, aprendizaje automáticoAbstract
Este trabajo propone un enfoque basado en ingeniería de características para detectar estrategias persuasivas en textos de memes políticos. Se definieron cuatro grupos de metavariables: (i) retóricas, (ii) de sentimiento y discurso de odio, (iii) estructurales y (iv) contextuales. Los experimentos utilizaron el conjunto de datos de la Task 4 de la competición SemEval-2024, con 7000 instancias de entrenamiento y 1000 de prueba. Se evaluaron los algoritmos de Random Forest y Regresión Logística con y sin tratamiento del desequilibrio entre las clases en el conjunto de datos de entrenamiento. El mejor resultado, con una puntuación F1 macro de 0,701, se obtuvo al combinar los grupos de metavariables retóricas y estructurales. El enfoque propuesto ofrece una alternativa computacionalmente eficiente e interpretable a los modelos basados en redes neuronales profundas.
Descargas
Citas
Anghelina, I., But , ă, G., and Enache, A. (2024). SuteAlbastre at SemEval-2024 task 4: Predicting propaganda techniques in multilingual memes using joint text and vision transformers. In Proc. of the 18th Int’l. Wksh on Semantic Evaluation (SemEval-2024), pages 443–449. ACL. DOI: 10.18653/v1/2024.semeval-1.68.
Aristóteles and Kennedy, G. A. (1991). On Rhetoric: A Theory of Civic Discourse. Oxford University Press.
Braca, A. and Dondio, P. (2023). Developing persuasive systems for marketing: the interplay of persuasion techniques, customer traits and persuasive message design. Ital. J. Mark, 2023:369—-412. DOI: 10.1007/s43039-023-00077-0.
Carvalho, J. and Plastino, A. (2021). On the evaluation and combination of state-of-the-art features in twitter sentiment analysis. Artif. Intell. Rev., 54(3):1887—-1936. DOI: 10.1007/s10462-020-09895-6.
Caseli, H. M. and Nunes, M. G. V., editors (2024). Processamento de Linguagem Natural: Conceitos, Técnicas e Aplicações em Português. BPLN, 3 edition.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. J. Artif. Int. Res., 16(1):321–357. DOI: 10.1613/jair.953.
Cruz, A. F., Rocha, G., and Cardoso, H. L. (2019). On sentence representations for propaganda detection: From hand-crafted features to word embeddings. In Proc. of the 2nd Wkshp on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 107–112. ACL. DOI: 10.18653/v1/D19-5015.
da Silva, P. N., Gonçalves, E. C., Rios, E. H., Muhammad, A., Moss, A., Pritchard, T., Glassborow, B., Plastino, A., and de Vasconcellos Azeredo, R. B. (2015). Automatic classification of carbonate rocks permeability from 1h nmr relaxation data. Expert Systems with Applications, 42(9):4299–4309. DOI: 10.1016/j.eswa.2015.01.034.
de Azevedo, A. B. S. and Gonçalves, E. C. (2025). An evaluation of meta-features for automated detection of persuasion in texts of political memes. In Anais do XIII Symposium on Knowledge Discovery, Mining and Learning, pages 145–152. SBC. DOI: 10.5753/kdmile.2025.247776.
de Morais, J. I., Abonizio, H. Q., Tavares, G. M., da Fonseca, A. A., and Barbon Jr, S. (2020). A multi-label classification system to distinguish among fake, satirical, objective and legitimate news in brazilian portuguese. iSys - Brazilian Journal of Information Systems, 13(4):126–149. DOI: 10.5753/isys.2020.833.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186. ACL. DOI: 10.18653/v1/N19-1423.
Dimitrov, D., Alam, F., Hasanain, M., Hasnat, A., Silvestri, F., Nakov, P., and Da San Martino, G. (2024). SemEval-2024 task 4: Multilingual detection of persuasion techniques in memes. In Proc. of the 18th Int’l. Wkshp on Semantic Evaluation (SemEval-2024), pages 2009–2026. ACL. DOI: 10.18653/v1/2024.semeval-1.275.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv, abs/2010.11929. DOI: 10.48550/arXiv.2010.11929.
Gonçalves, E. C., Plastino, A., and Freitas, A. A. (2013). A genetic algorithm for optimizing the label ordering in multi-label classifier chains. In 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, pages 469–476. IEEE. DOI: 10.1109/ICTAI.2013.76.
Guerini, M., Özbal, G., and Strapparava, C. (2015). Echoes of persuasion: The effect of euphony in persuasive communication. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1483–1493. ACL. DOI: 10.3115/v1/N15-1172.
Halversen, A. and Weeks, B. E. (2023). Memeing politics: Understanding political meme creators, audiences, and consequences on social media. Social Media + Society, 9(4):20563051231205588. DOI: 10.1177/20563051231205588.
Hu, M. and Liu, B. (2004). Mining and summarizing customer reviews. In Proc. of the 10th ACM SIGKDD Int’l. Conf. on Knowledge Discovery and Data Mining, page 168–177. ACM. DOI: 10.1145/1014052.1014073.
Hutto, C. and Gilbert, E. (2015). Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proc. of the 8th Int’l. Conf. on Weblogs and Social Media, pages 216–225. PKP|PS. DOI: 10.1609/icwsm.v8i1.14550.
Li, S., Wang, Y., Yang, L., Zhang, S., and Lin, H. (2024). LMEME at SemEval-2024 task 4: Teacher student fusion - integrating CLIP with LLMs for enhanced persuasion detection. In Proc. of the 18th Int’l. Wkshp on Semantic Evaluation (SemEval-2024), pages 628–633. ACL. DOI: 10.18653/v1/2024.semeval-1.92.
Mohamad, H. A. (2022). Analysis of rhetorical appeals to logos, ethos and pathos in ENL and ESL research abstracts. Malaysian Journal of Social Sciences and Humanities, 7(3). DOI: 10.47405/mjssh.v7i3.1314.
Navigli, R., Conia, S., and Ross, B. (2023). Biases in large language mdels: Origins, inventory, and discussion. J. Data and Information Quality, 15(2). DOI: 10.1145/3597307.
Piskorski, J., Stefanovitch, N., Bausier, V.-A., Faggiani, N., Linge, J., Kharazi, S., Nikolaidis, N., Teodori, G., De Longueville, B., Doherty, B., et al. (2023). News categorization, framing and persuasion techniques: Annotation guidelines. Technical Report JRC132862, European Commission, Ispra.
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In Proc. of the 38th Int’l. Conf. on Machine Learning, volume 139, pages 8748–8763. PMLR.
Santos, J., Alves, A., and Gonçalo Oliveira, H. (2019). Asapppy: a python framework for portuguese STS. In Proceedings of the ASSIN 2 Shared Task: Evaluating Semantic Textual Similarity and Textual Entailment in Portuguese co-located with XII Symposium in Information and Human Language Technology (STIL 2019), volume 2583, pages 14–26. CEUR-WS.org.
Sjoberg, D. D., Whiting, K., Curry, M., Lavery, J. A., and Larmarange, J. (2021). Reproducible summary tables with the gtsummary package. The R Journal, 13:570–580. DOI: 10.32614/RJ-2021-053.
Takahashi, H. (2024). Hidetsune at SemEval-2024 task 4: An application of machine learning to multilingual propagandistic memes identification using machine translation. In Proc. of the 18th Int’l. Wkshp on Semantic Evaluation (SemEval-2024), pages 370–373. ACL. DOI: 10.18653/v1/2024.semeval-1.57.
Vargas, F., Carvalho, I., Pardo, T. A. S., and Benevenuto, F. (2025). Context-aware and expert data resources for brazilian portuguese hate speech detection. Natural Language Processing, 31(2):435––456. DOI: 10.1017/nlp.2024.18.
Vargas, F., Jaidka, K., Pardo, T., and Benevenuto, F. (2023). Predicting sentence-level factuality of news and bias of media outlets. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 1197–1206. INCOMA Ltd., Shoumen, Bulgaria".
Weiss, M. C. (2019). Sociedade sensoriada: a sociedade da transformação digital. Estudos Avançados, 33(95):203—-214. DOI: 10.1590/s0103-4014.2019.3395.0013.
Witten, I. H., Frank, E., and Hall, M. A. (2011). Data mining: Practical machine learning tools and techniques. Morgan Kaufmann Publishers Inc., 3rd edition.
Yu, E., Wang, J., Qiao, X., Qi, J., Li, Z., Lin, H., Zong, L., and Xu, B. (2024). DUTIR938 at SemEval-2024 task 4: semi-supervised learning and model ensemble for persuasion techniques detection in memes. In Proc. of the 18th Int’l. Wkshp on Semantic Evaluation (SemEval-2024), pages 642–648. ACL. DOI: 10.18653/v1/2024.semeval-1.94.
Descargas
Published
Cómo citar
Issue
Section
Licencia
Derechos de autor 2026 Os autores
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
