Métodos de Procesado del Lenguaje Natural aplicados al estudio de las coberturas mediáticas

Mar Castillo-Campos; David Becerra-Alonso; David Varona-Aramburu

doi:10.35951/v4i2.171

Mar Castillo-Campos Universidad Loyola Andalucía http://orcid.org/0000-0003-1931-1493
David Becerra-Alonso Universidad Loyola Andalucía http://orcid.org/0000-0001-5174-7743
David Varona-Aramburu Universidad Complutense de Madrid http://orcid.org/0000-0001-8972-0490

Palabras clave: PLN, NLP, media coverage, cobertura mediática, procesado del lenguaje natural, natural language processing

Resumen

El Procesamiento del Lenguaje Natural comprende distintas técnicas cuantitativas para el análisis de textos y, aunque de probada solvencia, aún es infrecuente en el estudio del periodismo. La propuesta metodológica de esta investigación se ha diseñado para el análisis de la cobertura en medios de comunicación de las elecciones a la Asamblea de Madrid celebradas en 2021, y se desarrolla en tres fases: conteo de términos, estudio de relación entre binomios de conceptos mediante redes neuronales y agrupación y proyección de términos. Los resultados se han comparado con estudios previos de cobertura mediática realizados con otros métodos. Esta investigación muestra que la mecanización y la automatización de las técnicas propuestas es eficiente y sirve además como punto de partida para investigaciones cualitativas o mixtas que exploran textos en profundidad. La flexibilidad del método permite además experimentar con distintos grupos de palabras de medios de comunicación o cualquier otra fuente documental.

Biografía del autor/a

Mar Castillo-Campos, Universidad Loyola Andalucía

Mar Castillo-Campos has a degree in Communication, and a master's degree in Research Methods. She is currently working at Universidad Loyola Andalucía as a research assistant and PhD student, integrating quantitative methodologies and data science in the field of journalism.

David Becerra-Alonso, Universidad Loyola Andalucía

David Becerra-Alonso obtained his PhD in the School of Computing at the University of the West of Scotland, where he worked on dynamical chaotic systems. David currently holds a position as a lecturer at Universidad Loyola Andalucía. His research interests include dynamical systems, emergent collective behavior, and machine learning techniques and heuristics.

David Varona-Aramburu, Universidad Complutense de Madrid

David Varona-Aramburu has a PhD in Journalism and currently works at the Journalism and New Media Department at Universidad Complutense de Madrid. David has worked for more than 20 years in the media, and does research in Communication and Media.

Citas

Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python. O'Reilly Media.

Berven, A., Christensen, O., Moldeklev, S., Opdahl, A., & Villanger, K., (2020). A knowledge-graph platform for newsrooms. Computers in Industry 123. https://doi.org/10.1016/j.compind.2020.103321

Campos, R., Mangaravite, V., Pasquali, A., Jorge, A., Nunes, C., & Jatowt, A. (2020). YAKE! Keyword extraction from single documents using multiple local features. Information Sciences, 509, 257-289. https://doi.org/10.1016/j.ins.2019.09.013

Casero-Ripollés, A., Feenstra, R., & Tormey, S. (2016). Old and New Media Logics in an Electoral Campaign The Case of Podemos and the Two-Way Street Mediatization of Politics. The International Journal of Press/Politics, 21(3), 378-397. https://doi.org/10.1177/1940161216645340

Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., & Lopez, A. (2020). A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing, 408, 189-215. https://doi.org/10.1016/j.neucom.2019.10.1

Christian, H., Agus, M. P., & Suhartono, D. (2016). Single document automatic text summarization using term frequency-inverse document frequency (TF-IDF). ComTech: Computer, Mathematics and Engineering Applications, 7(4), 285-294. https://doi.org/10.21512/comtech.v7i4.3746

Doan, S., Yang, E. W., Tilak, S. S., Li, P. W., Zisook, D. S., & Torii, M. (2019). Extracting health-related causality from twitter messages using natural language processing. BMC medical informatics and decision making, 19(3), 71-77. https://doi.org/10.1186/s12911-019-0785-0

Edell, A. (2018). I trained fake news detection AI with >95% accuracy, and almost went crazy. En Towards Data Science. https://towardsdatascience.com/i-trained-fake-news-detection-ai-with-95-accuracy-and-almost-went-crazy-d10589aa57c

Emadi, M., & Rahgozar, M. (2020). Twitter sentiment analysis using fuzzy integral classifier fusion. Journal of Information Science, 46(2), 226-242. https://doi.org/10.1177/0165551519828

Fenoll, V., & Rodríguez-Ballesteros, P. (2017). Análisis automatizado de encuadres mediáticos. Cobertura en prensa del debate 7D 2015: el debate decisivo. Profesional de la Información, 26(4), 630-640. https://doi.org/10.3145/epi.2017.jul.07

Gao, Z., Feng, A., Song, X., & Wu, X. (2019). Target-dependent sentiment classification with BERT. IEEE Access 7, 154290-154299. https://10.1109/ACCESS.2019.2946594

García-Marín, J., Calatrava García, A., & Luengo, Ó. G. (2018). Debates electorales y conflicto. Un análisis con máquinas de soporte virtual (SVM) de la cobertura mediática de los debates en España desde 2008. Profesional de la información 27(3). https://doi.org/10.3145/epi.2018.may.15

Goularas, D., & Kamis, S. (2019, August). Evaluation of deep learning techniques in sentiment analysis from twitter data. In 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications, pp. 12-17. IEEE. https://doi.org/10.1109/Deep-ML.2019.00011

Iyengar, S., & Simon, A. F. (2000). New perspectives and evidence on political communication and campaign effects. Annual review of psychology, 51(1), 149- 169. https://doi.org/10.1146/annurev.psych.51.1.149

Jang, B., Kim, I., & Kim, J. (2019). Word2vec convolutional neural networks for classification of news articles and tweets. PloS one, 14(8). https://doi.org/10.1371/journal.pone.0220976

Jung, N., & Lee, G. (2019). Automated classification of building information modeling (BIM) case studies by BIM use based on natural language processing (NLP) and unsupervised learning. Advanced Engineering Informatics, 41, 100917. https://doi.org/10.1016/j.aei.2019.04.007

Kim, D., Seo, D., Cho, S., & Kang, P. (2019). Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec. Information Sciences, 477, 15-29. https://doi.org/10.1016/j.ins.2018.10.006

Kowsari, K., Jafari Meimandi, K., Heidarysafa, M., Mendu, S., Barnes, L., & Brown, D. (2019). Text classification algorithms: A survey. Information, 10(4), 150. https://doi.org/10.3390/info10040150

Kuncoro, B.A., & Iswanto, B.H. (2015, November). TF-IDF method in ranking keywords of Instagram users' image captions. En 2015 International Conference on Information Technology Systems and Innovation (ICITSI) (pp. 1-5). IEEE. https://ieeexplore.ieee.org/document/7437705

Labio-Bernal, A. (2018). Anti-communism and the mainstream online press in Spain: Criticism of Podemos as a strategy of a two-party system in crisis. The Propaganda Model Today: Filtering Perceptions and Awareness. University of Westminster Press. https://doi.org/10.16997/book27

Le, Q., & Mikolov, T. (2014). Distributed representations of sentences and documents. In International conference on machine learning, (pp. 1188-1196). PMLR. https://doi.org/10.48550/arXiv.1405.4053

Li, L., Johnson, J., Aarhus, W., & Shah, D. (2022). Key factors in MOOC pedagogy based on NLP sentiment analysis of learner reviews: What makes a hit. Computers & Education, 176, 104354. https://doi.org/10.1016/j.compedu.2021.104354

Mancera-Rueda, A., & Villar-Hernández, P. (2020). Análisis de las estrategias de encuadre discursivo en la cobertura electoral sobre Vox en los titulares de la prensa española. Doxa Comunicación. Revista Interdisciplinar de Estudios de Comunicación y Ciencias Sociales, 315-340. https://doi.org/10.31921/doxacom.n31a16

Marshall, M. N. (1996). Sampling for qualitative research. Family practice, 13(6), 522-526. https://doi.org/10.1093/fampra/13.6.522

McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.

McNair, B. (2017). An introduction to political communication. Routledge.

Miguel-Sáez-de-Urabain, A., Fernández-de-Arroyabe-Olaortua, A., & Lazkano-Arrillaga, I. (2017). La espectacularización de la información política. El caso de El País en las elecciones estadounidenses de 2016. Revista Latina De Comunicación Social 72, 1131-1147. https://doi.org/10.4185/RLCS-2017-1211

Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781

Müller, M., Salathé, M., & Kummervold, P. E. (2020). Covid-twitter-bert: A natural language processing model to analyse covid-19 content on twitter. arXiv preprint arXiv:2005.07503

Paniagua-Rojano, F., Seoane-Pérez, F., & Magallón-Rosa, R. (2020). Anatomía del bulo electoral: la desinformación política durante la campaña del 28-A en España. Revista CIDOB d'Afers Internacionals 124, 123-146. https://doi.org/10.24241/rcai.2020.124.1.123

Qaiser, S., & Ali, R. (2018). Text mining: use of TF-IDF to examine the relevance of words to documents. International Journal of Computer Applications, 181(1), 25-29. https://doi.org/10.5120/ijca2018917395

Salton, G., Buckley, C. (1988). Term-Weighting approaches in Automatic Text Retrieval. Information Processing and Management, 24(5), 513–523. https://doi.org/10.1016/0306-4573(88)90021-0

Sánchez Gutiérrez, B. (2016). La representación mediática de los partidos políticos emergentes: el caso de Podemos y Ciudadanos en Atresmedia (Trabajo Final de Máster). Universidad de Sevilla.

Sánchez-Gutiérrez, B., & Nogales-Bocio, A. I. (2018). La cobertura mediática de Podemos en la prensa nativa digital neoliberal española: una aproximación al caso de OkDiario, El Español y El Independiente. En A.I. Nogales Bocio, C. Marta-Lazo, M.A. Solans García (Ed.), Estándares e indicadores para la calidad informativa en los medios digitales, (pp. 125-146).

Shapiro, A. H., Sudhof, M., & Wilson, D. (2020). Measuring news sentiment. Journal of Econometrics 228(2), 221-243. https://doi.org/10.1016/j.jeconom.2020.07.053

Singh, K., Sen, I., & Kumaraguru, P. (2018, July). A Twitter corpus for Hindi-English code mixed POS tagging. En Proceedings of the sixth international workshop on natural language processing for social media, (pp. 12-17). https://doi.org/10.18653/v1/W18-3503

Sun, S., Luo, C., & Chen, J. (2017). A review of natural language processing techniques for opinion mining systems. Information fusion, 36, 10-25. https://doi.org/10.1016/j.inffus.2016.10.004

Thavareesan, S., & Mahesan, S. (2020, July). Sentiment lexicon expansion using Word2vec and fastText for sentiment prediction in Tamil texts. En 2020 Moratuwa Engineering Research Conference, (pp. 272-276). IEEE. https://doi.org/10.1109/MERCon50084.2020.9185369

Tian, X., & Tong, W. (2010). An improvement to TF: Term distribution based term weight algorithm. En 2010 Second International Conference on Networks Security, Wireless Communications and Trusted Computing 1, (pp. 252-255). IEEE. https://doi.org/10.1109/NSWCTC.2010.66

Xia, T., & Chai, Y. (2011). An Improvement to TF-IDF: Term Distribution based Term Weight Algorithm. Journal of Software, 6(3), 413-420. http://www.jsoftware.us/vol6/jsw0603-9.pdf

Vermeulen, M., Smith, K., Eremin, K., Rayner, G., & Walton, M. (2021). Application of Uniform Manifold Approximation and Projection (UMAP) in spectral imaging of artworks. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 252, 119547. https://doi.org/10.1016/j.saa.2021.119547

Wongso, R., Luwinda, F. A., Trisnajaya, B. C., & Rusli, O. (2017). News article text classification in Indonesian language. Procedia Computer Science, 116, 137-143. https://doi.org/10.1016/j.procs.2017.10.039

Zhou, P., Shi, W., Zhao, J., Huang, K-H., Chen, M., & Chang, K-W. (2019). Analyzing and Mitigating Gender Bias in Languages with Grammatical Gender and Bilingual Word Embeddings. ACL