Strategies for Automatic Detection of Fallacious Arguments in Political Speeches during Electoral Campaigns in Mexico
Kenia NIETO-BENITEZ,
Noe Alejandro CASTRO-SANCHEZ CASTRO-SANCHEZ,
Hector Jimenez SALAZAR,
Gemma BEL-ENGUIX,
Dante MÚJICA VARGAS,
Juan Gabriel GONZÁLEZ SERNA,
Nimrod GONZÁLEZ FRANCO https://doi.org/10.15514/ISPRAS-2024-36(1)-17
Abstract
This study proposes a machine learning approach to automatically detect "appeal to emotion" fallacies. The objective is to establish a set of elements that enable the application of fallacy mining. Our method uses a lexicon of emotions to distinguish valid arguments from fallacies, employing Support Vector Machine and Multilayer Perceptron models. The Multilayer Perceptron obtained an F1 score of 0.60 in identifying fallacies. Based on our analysis, we suggest using lexical dictionaries to effectively identify "appeal to emotion" fallacies.
Supporting agencies: This work was partially supported by the Government of Mexico (CONACYT grant with project number 653661, SNI).
About the Authors
Kenia NIETO-BENITEZ
Tecnológico Nacional de México, Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET)
Mexico
Mexico
Doctoral student in Computer Science at Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET). She received the master’s degree in computer science from TecNM/CENIDET in 2017. She currently works in Natural Language Processing, especially in the study of language of political discourse. Her current research interests include NLP, machine learning and the denaturation of language.
Noe Alejandro CASTRO-SANCHEZ CASTRO-SANCHEZ
Tecnológico Nacional de México, Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET)
Mexico
Mexico
Completed his master's and doctoral studies at the Research Center in Computing of the National Polytechnic Institute, specializing in Natural Language Processing. He is a member of the National Researchers System, a board member of the Mexican Society of Artificial Intelligence, and a member of the Latin American Association of Language Technologies. He serves as a faculty member at the National Center for Research and Technological Development (CENIDET).
Hector Jimenez SALAZAR
Universidad Autonoma Metropolitana
Mexico
Mexico
Studied for a bachelor's degree in mathematics and later a master's and PhD in computer science. He has been an active member of the Mexican Natural Language Processing Association for more than 15 years. He has taught computing at the Autonomous University of Puebla, and since 2007 he has been a professor at the Autonomous Metropolitan University. In addition to his interest in NLP is the feedback in the teaching-learning process.
Gemma BEL-ENGUIX
Universidad Nacional Autónoma de México
Mexico
Mexico
PhD in Computational Linguistics from the Rovira i Virgili University (Tarragona). Since 2016 she is a researcher at the Instituto de Ingeniería, at the Universidad Nacional Autónoma de Mexico. She currently works in Natural Language Processing, especially in the study of language of social platforms, graphs, complexity and detection of sexism and aggresive language. She is the editor of 8 books and author of more than 100 research articles in indexed journals, book chapters and conference proceedings.
Dante MÚJICA VARGAS
Tecnológico Nacional de México, Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET)
Mexico
Mexico
Received the Ph.D. degree in Communications and Electronics from Seccion de Estudios de Posgrado e Investigación, ESIME-Culhuacán, Instituto Politécnico Nacional in Mexico. He is a professor from 2015 at the Departamento de Ciencias Computacionales, Tecnológico Nacional de México/Centro Nacional de Investigación y Desarrollo Tecnológico. His current research interests include deep learning, machine learning, fuzzy clustering, neuro-fuzzy systems, digital signal processing and biomedical applications.
Juan Gabriel GONZÁLEZ SERNA
Tecnológico Nacional de México, Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET)
Mexico
Mexico
Earned his Ph.D. in Computer Science from the Research Center in Computing of the National Polytechnic Institute (CIC-IPN) in 2006. He obtained a Master's degree in Computer Science from the National Research and Technological Development Center (TecNM/CENIDET) in 1995. He has been a Professor-Researcher in the Department of Computer Science at TecNM/CENIDET since 1995 to the present. His research areas include Human-Computer Interaction, Affective Computing and Sentiment Analysis, and User Experience (UX) Evaluation.
Nimrod GONZÁLEZ FRANCO
Tecnológico Nacional de México, Centro Nacional de Investigación y Desarrollo Tecnológico (TecNM/CENIDET)
Mexico
Mexico
Joined TecNM/CENIDET, located in Cuernavaca, Mexico, as a research professor in the field of Intelligent Hybrid Systems in 2019. He has served as a reviewer for scientific articles across multiple journals and conferences, including prominent events like the World Multi-Conference on Systemics, Cybernetics and Informatics, as well as the Mexican International Conference on Artificial Intelligence. His research spans diverse areas, with a focus on brain-computer interface systems and machine learning.
References
1. Wells G. Minería de falacias en el discurso político. Grade Thesis, Barcelona: Universidad de Barcelona, 2018.
2. Kacprzak M., Sawicka A. Identification of formal fallacies in a natural dialogue, Fundamenta Informaticae, vol. 135, no. 4, 2014, pp. 403-417.
3. Kacprzak M., Yaskorska O. Dialogue protocols for formal fallacies, Argumentation, vol. 28, no. 3, 2014, pp. 349-369.
4. Van Eemeren F.H., Garssen B., Meuffels B. Fallacies and judgments of reasonableness: Empirical research concerning the pragma-dialectical discussion rules, Springer, 2009.
5. Dowden B. Fallacies. The Internet Encyclopedia of Philosophy. https://iep.utm.edu/fallacy/. Accessed may, 2019.
6. Lippi M., Torroni P. Argumentation mining: State of the art and emerging trends, ACM Transactions on Internet Technology, vol. 16, no. 2, 2016, pp. 1-25. https://doi.org/10.1145/2850417.
7. Copi I.M., Cohen C. Introducción a la lógica, México: Limusa, 2013
8. Capaldi N. Como Ganar una Discusión: El Arte de la Argumentación, Barcelona: Gedisa, 2011.
9. Hansen, H. Fallacies. Stanford Encyclopedia of Philosophy Archive. https://plato.stanford.edu/archives/fall2019/info.html. Accessed December 2019].
10. Vega R.L. La fauna de las falacias, Madrid: Trotta, 2013.
11. Van Eemeren F.H. Grootendorst R. Fallacies in pragma-dialectical perspective, Argumentation, vol. 1, no. 3, 1987, pp. 283-301. https://doi.org/10.1007/BF00136779.
12. Van Eemeren F.H., Grootendorst R. Argumentación, comunicación y falacias: una perspectiva pragma-dialéctica, Chile: Ediciones universidad católica de chile, 2002.
13. Weston A. Las claves de la argumentación, Barcelona: Ariel, 2006.
14. Damer T.E. Attacking Faulty Reasoning: A Practical Guide to Fallacy-Free Arguments, Estados Unidos: Wadsworth Pub Co, 2009.
15. Zurloni V., Anolli L. Fallacies as argumentative devices in political debates, International Workshop on Political Speech, pp. 245-257, 2013. https://doi.org/10.1007/978-3-642-41545-6_18.
16. Harada O.E. 2009: Argumentos, formalización y lógica informal, CIENCIA ergo-sum, vol.16, no. 2, 2009, pp. 125-13.
17. Jason G. Fallacies are common, Informal Logic, vol. 11, no. 2, 1989, pp. 101-106. https://doi.org/10.22329/il.v11i2.2624.
18. Jason G. Are Fallacies Common? A Look at Two Debates, Informal Logic, vol. 8, no. 2, 1986, pp. 81-92. https://doi.org/10.22329/il.v8i2.2685.
19. Santoso J.M.A. Fallacy Analysis of the Arguments on the First US Presidential Debate Between Hillary Clinton and Donald Trump, Kata Kita, vol. 5, no. 2, 2017, pp. 65-71.
20. Blassnig S., Büchel F., Ernst N., Engesser S. Populism and Informal Fallacies: An Analysis of Right-Wing Populist Rhetoric in Election Campaigns, Argumentation, vol. 33, no. 1, 2018, pp. 107-136. https://doi.org/10.1007/s10503-018-9461-2.
21. Cabrejas-peñuelas A.B. Manipulation in Spanish and American pre-election political debates: The Rajoy–Rubalcaba vs. Obama–McCain debates, Intercultural Pragmatics, vol. 12, no. 4, 2015, pp. 515–546. https://doi.org/10.1515/ip-2015-0025.
22. Warman J.S., Hamzah H. An Analysis of Logical Fallacy on Prabowo Subianto's Argumentation during 2019 Indonesia Presidential Debate, Lingua Didaktika: Jurnal Bahasa dan Pembelajaran Bahasa, vol. 14, no. 1, 2020, pp. 70-80.
23. Hameed S.K., Al-Asadi R.A.N.M. Analysis of Fallacies in Hillary and Trump's Second Presidential Debate, International Journal of English Literature and Social Sciences, vol. 3, no. 4, 2018, pp. 625-635.
24. Al-Hindawi F.H., Alkhazaali M.A., Al-Awadi D. A Pragmatic Study of Fallacy in David Cameron’s Political Speeches, Journal of Social Science Studies, vol. 2, no. 2, 2015, pp. 214-239.
25. Greenwell W.S., Knight J.C., Holloway C.M. Pease J. J. A Taxonomy of Fallacies in System Safety Arguments. International System Safety Conference, pp. 1-10, 2006.
26. Neuman Y., Weinstock M.P., Glasner A. The effect of contextual factors on the judgement of informal reasoning fallacies, Quarterly Journal of Experimental Psychology, vol. 59, no. 2, 2006, pp. 411-425.
27. Hiba B. When Education Becomes an Empowering Act: Learning Fallacies Analysis, American Journal of Educational Research, vol. 8, no. 9, 2020, pp. 731-738.
28. Tobolka S. J. Competencia de los hablantes en la identificación de falacias: una perspectiva pragma-dialéctica, Onomázein, vol. 15, 2007, pp. 129-155. https://doi.org/10.7764/onomazein.15.05.
29. Morales G.I.M. Falacias en los discursos de los candidatos presidenciales en México (2012), Revista latinoamericana de estudios del discurso, vol. 12, no. 2, 2016, pp. 11-32.
30. Nieto-Benitez K., Castro-Sánchez N. A., Salazar H. J., Bel-Enguix G. Corpus de falacias por apelación a las emociones: una aproximación a la identificación automática de falacias, Linguamática, vol. 14, no. 2, 2022, pp. 59-72.
31. Camargo L.S.P. La construcción de la emoción en los discursos políticos de campaña, Pragmalingüística, vol. 26, 2018, pp. 199-220.
32. Johnson R. H. Manifest rationality: A pragmatic theory of argument, Routledge, 2000.
33. Gilbert M.A. Emotion, argumentation and informal logic, Informal Logic, vol. 24, no. 3, 2004, pp. 245-264. https://doi.org/10.22329/il.v24i3.2147.
34. Walton D.N. A Pragmatic Theory of Fallacy, London: University of Alabama Press, 1995.
35. Tindale C.W. Fallacies and argument appraisal, Nueva York: Cambridge University Press, 2007.
36. Walton D.N. Informal logic: A handbook for critical argument, Cambridge University Press, 1989.
37. Walton D.N. Dialogue theory for critical thinking, Argumentation, vol. 3, no. 2, 1989, pp. 169-184.
38. Pirie M. How to Win Every Argument: The Use and Abuse of Logic, Lodon/New York: Continuum, 2006.
39. Govier T. A Practical Study of Argument, Estados Unidos: Cengage Learning, 2013.
40. Lawrence, J., Reed, C. Argument mining: A survey, Computational Linguistics, vol. 45, no. 4, 2020, pp. 765-818. https://doi.org/10.1162/coli_a_00364.
41. Cabrio E., Villata S. Five Years of Argument Mining: a Data-driven Analysis, IJCAI, vol. 18, pp. 5427-5433, 2018.
42. Garcia-Gorrostieta J.M., Lopez-Lopez A. Argument component classification in academic writings, Journal of Intelligent & Fuzzy Systems, vol. 34, no. 5, 2018, pp. 3037-3047.
43. Garcia-Gorrostieta J.M., Lopez-Lopez A. A corpus for argument analysis of academic writing: argumentative paragraph detection, Journal of Intelligent and Fuzzy Systems, vol. 36, no. 5, 2019, pp. 4565-4577. 10.3233/JIFS-179008.
44. García‐Gorrostieta J.M., López‐López A., González‐López S. Automatic argument assessment of final project reports of computer engineering students, Computer Applications in Engineering Education, vol. 26, no. 5, 2018, pp. 1217-1226.
45. Stab C., Gurevych I. “Recognizing insufficiently supported arguments in argumentative essays,” Proceedings of th 15th Conference of the European Chapter of the Association for Computational Linguistics, vol. 1, pp. 980-990, 2017.
46. Habernal I., and Gurevych I. “What makes a convincing argument? empirical analysis and detecting attributes of convincingness in web argumentation,” Conference on Empirical Methods in Natural Language Processing, pp. 1214-1223, 2016.
47. Molina-González M. D., Martínez-Cámara E., Martín-Valdivia M. T., Perea-Ortega J. M. Semantic orientation for polarity classification in Spanish reviews, Expert Systems with Applications, vol. 40, no. 18, 2013, pp. 7250-7257.
48. Rangel I.D., Sidorov G., Suárez-Guerra S. Creación y evaluación de un diccionario marcado con emociones y ponderado para el español, Onomazein, vol. 29, 2014, pp. 31-46.
49. Brezina V. Statistics in Corpus Linguistics: A Practical Guide, Cambridge: Cambridge University Press, 2018.
50. Habernal I., Gurevych I. Argumentation mining in user-generated web discourse, Computational Linguistics, vol. 43, no. 1, 2017, pp. 125-179.
51. Sierra M.G. Introducción a los Corpus Lingüísticos. México: Universidad Nacional Autónoma de México-Instituto de Ingeniería, 2017.
Review
For citations:
NIETO-BENITEZ K., CASTRO-SANCHEZ N.C., SALAZAR H., BEL-ENGUIX G., MÚJICA VARGAS D., GONZÁLEZ SERNA J., GONZÁLEZ FRANCO N. Strategies for Automatic Detection of Fallacious Arguments in Political Speeches during Electoral Campaigns in Mexico. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2024;36(1):259-276. https://doi.org/10.15514/ISPRAS-2024-36(1)-17
Email this article 