Minería de comentarios en la red social X sobre la percepción de la seguridad en la ciudadanía ecuatoriana
Mining comments from the social network x on the security perceptions of Ecuadorian citizens
DOI:
https://doi.org/10.53591/iti.v17i24.2609Keywords:
public safety, text mining, social media, sentiment analysis, LDA, EcuadorAbstract
Context: In the current context of growing attention to citizen security in Ecuador, social media has become a space where collective perceptions about violence and crime are expressed. Objective: The purpose of this study is to analyze posts extracted from social media platform X (formerly Twitter) in order to identify discursive patterns linked to insecurity, using computational techniques applied to textual data. Technique: The sample consisted of more than 2,000 geolocated posts in six cantons: Guayaquil, Quito, Cuenca, Portoviejo, Manta, and Durán, collected in six rounds between June and July 2025. Preprocessing included duplicate removal, lexical normalization, and token analysis. Text mining techniques such as term frequency analysis, bigram generation, lexical sentiment classification, and thematic modeling were used. Results: The analysis revealed a high recurrence of terms linked to criminal acts and a predominance of messages with negative polarity, particularly in Guayaquil, Manta, and Durán. Using the Latent Dirichlet Allocation (LDA) classification model, five recurring topics were identified that group together different discursive expressions about insecurity. Additionally, the use of other classification models, such as Naive Bayes, is suggested to estimate the polarity of new posts, utilizing a higher proportion of previously labeled data. Conclusion: This study emphasizes the significance of natural language processing in conjunction with classification techniques to identify patterns of interest within the country's citizen security, as perceived by social media users.
References
Adams, jimi, & Lubbers, M. J. (2022). Social Network Data Collection: Principles and Modalities. SSRN Electronic Journal. https://doi.org/10.2139/SSRN.4216936
Adams, jimi, Santos, T., & Williams, V. N. (2021). Strategies for Collecting Social Network Data. The Oxford Handbook of Social Networks, 117–136. https://doi.org/10.1093/OXFORDHB/9780190251765.013.10
Alghamdi, R., & Alfalqi, K. (2015). A Survey of Topic Modeling in Text Mining. International Journal of Advanced Computer Science and Applications, 6(1). https://doi.org/10.14569/IJACSA.2015.060121
Avasthi, S., Chauhan, R., & Acharjya, D. P. (2022). Topic modeling techniques for text mining over large-scale scientific and biomedical text corpus. International Journal of Ambient Computing and Intelligence, 13(1). https://doi.org/10.4018/IJACI.293137
Bai, J. (2022). Design and Implementation of Data Analysis System of Social Network. International Journal of Frontiers in Sociology, 4(2). https://doi.org/10.25236/IJFS.2022.040215
Battle, H., Álvarez-Mon, M. Á., Lara-Abelenda, F. J., Perez-Araluce, R., & Pinto Da Costa, M. (2025). Attitudes towards mental health professionals in social media: infodemiology study. The British Journal of Psychiatry, 1–6. https://doi.org/10.1192/BJP.2024.261
Buenano-Fernandez, D., Gonzalez, M., Gil, D., & Lujan-Mora, S. (2020). Text Mining of Open-Ended Questions in Self-Assessment of University Teachers: An LDA Topic Modeling Approach. IEEE Access, 8, 35318–35330. https://doi.org/10.1109/ACCESS.2020.2974983
Chakravarty, U. K., & Arifuzzaman, S. (2024). Sentiment analysis of tweets on social security and medicare. Social Network Analysis and Mining, 14(1). https://doi.org/10.1007/S13278-024-01248-3
Chaparro, L. F., Pulido, C., Rudas, J., Victorino, J., Reyes, A. M., Estrada, C., Narvaez, L. A., & Gómez, F. (2021). Quantifying Perception of Security through Social Media and Its Relationship with Crime. IEEE Access, 9, 139201–139213. https://doi.org/10.1109/ACCESS.2021.3114675
Ferrara, E., & Yang, Z. (2015). Measuring Emotional Contagion in Social Media. PLOS ONE, 10(11), e0142390. https://doi.org/10.1371/JOURNAL.PONE.0142390
Figueroa-Campoverde, D. S. (2024). Análisis de sentimientos sobre la percepción de seguridad para la ciudad de Cuenca durante el año 2023 [Pontificia Universidad Católica del Ecuador]. https://repositorio.puce.edu.ec/server/api/core/bitstreams/496f879a-0dab-4ac0-bc9c-569852a7962a/content
Goyanes, M., López-López, P. C., & Demeter, M. (2021). Social Media in Ecuador: Impact on Journalism Practice and Citizens’ Understanding of Public Politics. Journalism Practice, 15(3), 366–382. https://doi.org/10.1080/17512786.2020.1724180;PAGE:STRING:ARTICLE/CHAPTER
Greco, F., & Polli, A. (2021). Security Perception and People Well-Being. Social Indicators Research, 153(2), 741–758. https://doi.org/10.1007/S11205-020-02341-8
Guo, J., Liu, N., Wu, Y., & Zhang, C. (2021). Why do citizens participate on government social media accounts during crises? A civic voluntarism perspective. Information & Management, 58(1), 103286. https://doi.org/10.1016/J.IM.2020.103286
Hawkins, J. B., Brownstein, J. S., Tuli, G., Runels, T., Broecker, K., Nsoesie, E. O., McIver, D. J., Rozenblum, R., Wright, A., Bourgeois, F. T., & Greaves, F. (2016). Measuring patient-perceived quality of care in US hospitals using Twitter. BMJ Quality & Safety, 25(6), 404–413. https://doi.org/10.1136/BMJQS-2015-004309
Highfield, T., & Miltner, K. M. (2023). Platformed solidarity: Examining the performative politics of Twitter hashflags. Convergence, 29(6), 1641–1667. https://doi.org/10.1177/13548565231199981/ASSET/FF235F2C-9F65-4354-A4D6-4AFC1B9EBC31/ASSETS/IMAGES/LARGE/10.1177_13548565231199981-FIG11.JPG
Hodorog, A., Petri, I., & Rezgui, Y. (2022). Machine learning and Natural Language Processing of social media data for event detection in smart cities. Sustainable Cities and Society, 85. https://doi.org/10.1016/J.SCS.2022.104026
Jani, J. A., Cowan, D., Ouonkap, L., Adesina, D., Ma, T., Chen, S., Aldakhil, S., & Hoang, K. B. (2025). Missing the message to brain tumor patients: a 2023 twitter analysis among patients, informal caregivers, and healthcare professionals in glioblastoma multiforme. Journal of Neuro-Oncology. https://doi.org/10.1007/S11060-025-04948-8
Khemani, B., Malave, S., Patil, S., Shilotri, N., Varma, S., Vishwakarma, V., & Sharma, P. (2024). Sentimatrix: sentiment analysis using GNN in healthcare. International Journal of Information Technology. https://doi.org/10.1007/S41870-024-02142-Z
Kobayashi, V. B., Mol, S. T., Berkers, H. A., Kismihók, G., & Den Hartog, D. N. (2018). Text Mining in Organizational Research. Organizational Research Methods, 21(3), 733–765. https://doi.org/10.1177/1094428117722619
Kolyshkina, I., & Simoff, S. (2021). The CRISP-ML Approach to Handling Causality and Interpretability Issues in Machine Learning. Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021, 2306–2312. https://doi.org/10.1109/BIGDATA52589.2021.9671754
Kumar, S., Kar, A. K., & Ilavarasan, P. V. (2021). Applications of text mining in services management: A systematic literature review. Int. J. Inf. Manag. Data Insights, 1(1). https://doi.org/10.1016/J.JJIMEI.2021.100008
Lagrange, B. (2025). Emotions on Social Media as Catalysts for Change: Epistemic and Motivational Potentialities for Gender Equality. Media and Communication, 13, 8591. https://doi.org/10.17645/MAC.8591
McCarthy, S., Rowan, W., Mahony, C., & Vergne, A. (2023). The dark side of digitalization and social media platform governance: a citizen engagement study. Internet Res., 33(6), 2172–2204. https://doi.org/10.1108/INTR-03-2022-0142
Naranjo-Zolotov, M., Turel, O., Oliveira, T., & Lascano, J. E. (2021). Drivers of online social media addiction in the context of public unrest: A sense of virtual community perspective. Computers in Human Behavior, 121, 106784. https://doi.org/10.1016/J.CHB.2021.106784
Pandya, A., & Dave, B. (2025). INFLUENCE OF SOCIAL MEDIA ON STRESS AND QUALITY OF LIFE IN GENERATION Z-AN OBSERVATIONAL STUDY. Indian Journal of Physical Therapy, 6(1), 40–42. https://doi.org/10.63299/IJOPT.060112
Salah, Z., Al-Ghuwairi, A. R. F., Baarah, A., & Aloqaily, A. (2019). A systematic review on opinion mining and sentiment analysis in social media. International Journal of Business Information Systems, 31(4), 530–554. https://doi.org/10.1504/IJBIS.2019.101585
Sewalk, K. C., Tuli, G., Hswen, Y., Brownstein, J. S., & Hawkins, J. B. (2018). Using Twitter to Examine Web-Based Patient Experience Sentiments in the United States: Longitudinal Study. Journal of Medical Internet Research, 20(10). https://doi.org/10.2196/10043
Shakhayev, S. S. S., & Seyidova, I. S. I. (2023). BIG DATA PROCESSING WITH PYTHON IN SOCIAL NETWORKS. ETM - Equipment, Technologies, Materials, 16(04), 76–82. https://doi.org/10.36962/ETM16042023-76
Usman, M., Mujahid, M., Rustam, F., Flores, E. S., Mazón, J. L. V., de la Torre Díez, I., & Ashraf, I. (2024). Analyzing patients satisfaction level for medical services using twitter data. PeerJ Computer Science, 10. https://doi.org/10.7717/PEERJ-CS.1697
Valla, L. G. (2022). Citizens’ Perceptions of Security Issues: New and Old Actors in the National Security Framework. Journal of Human Security. http://www.librelloph.com/journalofhumansecurity/article/view/johs-18.1.18
Van Nguyen, P., Vrontis, D., Nguyen, L. D. P., Nguyen, T. T. U., & Salloum, C. (2025). Unraveling the Role of Citizens’ Concerns and Cognitive Appraisals in E-Government Adoption: The Impact of Social Media and Trust. Strategic Change.
