Revista de comunicación política e institucional

No. 60 (2025): Herramientas y estrategias visuales y textuales para la comunicación política
Articles

Textual Strategies in Political Communication: The Impact of Digital Nudging in the 2019 Elections in Bogotá, Medellín, and Cali, Colombia

PDF (Español (España))
DOI: https://doi.org/10.56151/maspoderlocal.259
Luciana C. Manfredi
Universidad ICESI
Martin Nader
Universidad Icesi

Keywords

  • elecciones,
  • digital nudging,
  • tuits,
  • persuasión
  • elections,
  • digital nudging,
  • persuasion,
  • tweets

How to Cite

Manfredi, L. C., & Nader, M. (2025). Textual Strategies in Political Communication: The Impact of Digital Nudging in the 2019 Elections in Bogotá, Medellín, and Cali, Colombia. Más Poder Local, (60), 72-88. https://doi.org/10.56151/maspoderlocal.259

Copyright (c) 2025 Of the author or authors

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Abstract

This article analyzes the phenomenon of digital nudging in publications of the social network X (formerly Twitter®) during the 2019 subnational electoral process in Colombia. Specifically, the accounts of candidates for mayor of the cities of Bogota, Medellin and Cali, identified as the three capital cities with the largest population within the Colombian territory, were reviewed. At a methodological level, 3.5 million tweets were extracted during the whole year 2019 issued in the accounts of all registered candidates and by other users of the mentioned network. With said information, we estimated the polarity of the messages, the number of tags present in the text, as well as the mentions of users, the number of times the publication was classified as favorite and retweeted, to finish with the number of words contained in the speech. Different algorithms were then tested to estimate the level of effectiveness in classifying tuits into one of two categories: nudge (tweets that have the explicit intention of provoking emotional reactions that lead the reader to vote for a candidate) or non-nudge (tweets that do not contain the linguistic elements to induce the social network user to vote for a candidate).

PDF (Español (España))

Downloads

Download data is not yet available.

References

  1. Aragón, P.; Kappler, K. E.; Kaltenbrunner, A.; Laniado, D. y Volkovich, Y. (2013): «Communication dynamics in twitter during political campaigns: The case of the 2011 Spanish national election: Communication Dynamics in Twitter During Political Campaigns». Policy & Internet, 5(2): 183-206. DOI: https://doi.org/10.1002/1944-2866.POI327
  2. Blei, D.; Ng, A. y Jordan, M. (2003): «Latent Dirichlet allocation». Journal of Machine Learning Research, 3 v.4–5; pp. 993-1022. DOI: https://doi.org/10.1162/jmlr.2003.3.4-5.993
  3. Box-Steffensmeier, J. M.; Darmofal, D. y Farrell, C. A. (2009): «The Aggregate Dynamics of Campaigns». The Journal of Politics, 71(1): 309-323. DOI: https://doi.org/10.1017/s0022381608090208
  4. Carsey, T. M.; Jackson, R. A.; Stewart, M. y Nelson, J. P. (2011): «Strategic Candidates, Campaign Dynamics, and Campaign Advertising in Gubernatorial Races». State Politics & Policy Quarterly, 11(3): 269-298.
  5. Ospina Celis, D. y Upegui, J. C. (2021): Estudio exploratorio sobre el uso de tecnologías digitales con fines político-electorales: Campana presidencial 2018 y Campañas a la Alcaldía de Bogotá 2015 y 2019. Londres: Privacy International.
  6. De la Garza Montemayor, D. J. y Gómez Díaz de León, C. (2024): «Inteligencia artificial y big data: nuevos paradigmas de la Comunicación Política y la Gobernanza Digital». Revista Más Poder Local, 56: 9-26. DOI: https://doi.org/10.56151/maspoderlocal.214
  7. Fridkin, K. L.; Kenney, P. J. (2011): «Variability in Citizens’ Reactions to Different Types of Negative Campaigns». American Journal of Political Science, 55(2): 307-325. DOI: https://doi.org/10.1111/j.1540-5907.2010.00494.x
  8. Gan, J. y Qi, Y (2021): «Selection of the Optimal Number of Topics for LDA Topic Model—Taking Patent Policy Analysis as an Example». Entropy, 23(1301): 1:45. DOI: https://doi.org/10.3390/e23101301
  9. Geer, J. G. (2012): «The News Media and the Rise of Negativity in Presidential Campaigns». PS: Political Science & Politics, 45(3): 422-427. DOI: https://doi.org/10.1017/S1049096512000492
  10. Günther, F.; Dudschig, C. y Kaup, B. (2015): «LSAfun—An R package for computations based on Latent Semantic Analysis». Behavior Research Methods, 47(4): 930–944.
  11. Harris, J. K. (2021): «Primer on binary logistic regression». Family Medicine and Community Health, vol. 9.; doi: 10.1136/fmch-2021-001290. PMID: 34952854; PMCID: PMC8710907.
  12. Jockers, M. (2020): «Introduction to the Syuzhet Package» (en línea). Disponible en: https://cran.r-project.org/web/packages/syuzhet/vignettes/syuzhet-vignette.html.
  13. Jung, A.; Stieglitz, S.; Kissmer, T.; Mirbabaie, M. y Kroll, T. (2022): «Click me…! The influence of clickbait on user engagement in social media and the role of digital nudging». PLoS ONE, 17 (6). DOI: https://doi.org/10.1371/journal.pone.0266743
  14. Jungherr, A. (2014): «The Logic of Political Coverage on Twitter: Temporal Dynamics and Content: Coverage on Twitter». Journal of Communication, 64(2): 239-259. DOI: https://doi.org/10.1111/jcom.12087
  15. Jurka, T.; Collingwood, L.; Boydstun, A.; Grossman, E. y van Atteveld, W. (2011): «RTextTools: A Supervised Learning Package for Text Classification». Recuperado de: http://install.rtexttools.com/files/ RTextTools_GettingStarted.pdf.
  16. López-Meri, A. (2015): «Redes sociales y campañas electorales: Twitter como fuente informativa en las elecciones catalanas del #25N». Comunicació. Revista de recerca i d’anàlisi [abans Treballs de Comunicació], 32(2): 115-137. DOI: https://doi.org/10.2436/tc.v32i2.139394
  17. Manfredi, L. C.; Abadía, A. A. y Sayago, J. T. (2021): «Twitter, sentimientos y precandidatos presidenciales. Comunicación en tiempos de paro nacional». Elecciones, 20(22): 309-336. DOI: https://doi.org/10.53557/Elecciones.2021.v20n22.09
  18. Manfredi, L. C.; González Sánchez, J. M.; Biojó Fajardo, D. (2019): «¡Twitteo, luego existo! Un análisis de las dinámicas de competencia electoral de los candidatos a la Presidencia de Colombia 2018 en Twitter». En: Elecciones Presidenciales y de Congreso 2018. Nuevos acuerdos ante diferentes desafíos, Fundación Konrad Adenauer Stiftung, p. 117.
  19. Manfredi, L.; González-Sánchez, J. M. (2019): «Comunicación y competencia en Twitter. Un análisis en las elecciones presidenciales Colombia 2018». Revista Estudios Institucionales, 6(11): 133-130. DOI: https://doi.org/10.5944/eeii.vol.6.n.11.2019.25086
  20. Meyers, L. S.; Gamst, G. y Guarino, A. J. (2013): Applied multivariate research: Design and interpretation (2nd ed.). New York: Sage Publications, Inc.
  21. Milanese, J. P.; Manfredi, L. C. (2018): «Nationalization of the Legislative Vote, Visibility and Reputation in the Written Press: An Analysis of Candidates’ Strategies for the 2014 Colombian Senate Election». Journal of Iberian and Latin American Research, 24(3): 199-213. DOI: https://doi.org/10.1080/13260219.2019.1623289
  22. Mohammad, S. y Turney, P. (2013): «Crowdsourcing a word-emotion association lexicon». Computational Intelligence, 29(3): 436-465.
  23. Molyneux, L. y Coddington, M. (2019): «Aggregation, Clickbait and Their Effect on Perceptions of Journalistic Credibility and Quality». Journalism Practice, 14(4): 429-446. DOI: https://doi.org/10.1080/17512786.2019.1628658
  24. Posit (2020): RStudio: Integrated Development for R. RStudio, PBC, Boston, MA.
  25. Reñosa M. D. C.; Landicho, J.; Wachinger, J.; Dalglish, S.L.; Bärnighausen, K.; Bärnighausen T. y McMahon, S. A. (2021): «Nudging toward vaccination: a systematic review». BMJ Global Health, 6(9). DOI: https://doi.org/10.1136/bmjgh-2021-006237
  26. Silge, J. y Robinson, D. (2016): Text Mining with R: A Tidy Approach. New York: O’Reilly.
  27. Stromer-Galley, J. y Rossini, P. (2023): «Categorizing political campaign messages on social media using supervised machine learning». Journal of Information Technology & Politics, 1-14. DOI: https://doi.org/10.1080/19331681.2023.2231436
  28. Tausczik, Y. R. y Pennebaker, J. W. (2010): «The psychological meaning of words: LIWC and computerized text analysis methods». Journal of Language and Social Psychology, 29(1): 24–54. DOI: https://doi.org/10.1177/0261927X09351676
  29. Thornhill, C.; Meeus Q.; Peperkamp J. y Berendt B. (2019): «A Digital Nudge to Counter Confirmation Bias». Frontiers in Big Data, 2(11). DOI: https://doi.org/10.3389/fdata.2019.00011
  30. Valta, M.; Menzel, J. y Maier, C. (2022): «Digital nudging: A Systematic Literature Review and Future Research Directions.» ACM Digital Library doi: 10.1145/3510606.3550211.
  31. Zhao, L.; Chen, F.; Dai, J.; Hua T.; Lu, C-T y Ramakrishnan N. (2014): «Unsupervised spatial event detection in targeted domains with applications to civil unrest modeling.» PLoS One, 9(10). DOI: https://doi.org/10.1371/journal.pone.0110206