Bayesian learning and social graphs for improving forecasts in social good analysis in political behavior
DOI:
https://doi.org/10.26507/paper.4539Keywords:
Aprendizaje bayesiano, Grafos sociales, inteligencia artifical, aprendizaje profundo, aprendizaje de máquina, Social Good, comportamiento PolíticoAbstract
Political behavior and social movements play an important role in today’s society, where human, cultural, emotional, and electoral relationships shape trends in processes of integration and participation in social welfare. This is known as “AI for Social Good (AI4SG),” which is implemented through computational models that leverage Artificial Intelligence (AI), Deep Learning (DL), and Machine Learning (ML) to improve performance metrics in data forecasting, unsupervised processes, and decision-making based on Natural Language Processing (NLP). These approaches enable outcomes in analysis, automation, simulation, diagnostics, and prediction across a variety of real-world contexts. Bayesian learning focuses on statistics for data analysis and interpretation, as well as the ability to manage knowledge through assertive data handling. Likewise, the social graph model facilitates the analysis of interactions between individuals, allowing for proximity-based pattern recognition in social behavior, supported by various tools and techniques. This doctoral thesis proposal centers on the integration of these two computational models for the social common good, supported by Artificial Intelligence to assess the impact on political science phenomena, particularly regarding community trends and reactions.
Author Biography
Jorge Enrique Otálora Luna, Universidad Pedagógica y Tecnológica de Colombia
Director de la Propuesta Doctoral
References
Abbasi, A., Chiang, R.H.L. and Xu, J.J. (2023) Data Science for Social Good.
Abbasimehr, H. and Paki, R. (2021) ‘Prediction of COVID-19 confirmed cases combining deep learning methods and Bayesian optimization’, Chaos, Solitons and Fractals, 142. Available at: https://doi.org/10.1016/j.chaos.2020.110511.
Abduallah, Y. et al. (2024) ‘Prediction of the SYM-H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification’, Space Weather, 22(2). Available at: https://doi.org/10.1029/2023SW003824.
De Andrea Sánchez, F.J. (2024) ‘partidos políticos y las elecciones en la era de la inteligencia artificial’, Revista de la Facultad de Derecho de México, 74(e), pp. 1015–1040. Available at: https://doi.org/10.22201/fder.24488933e.2024.e.88697.
Astobiza, A.M. (2021) ‘ARTIFICIAL INTELLIGENCE FOR SOCIAL GOOD (AI4SG): AI AND SUSTAINABLE DEVELOPMENT GOALS’, Arbor, 197(802). Available at: https://doi.org/10.3989/arbor.2021.802007.
Bustos, A. et al. (2008) andeva Para diseÑo comPletamente al aZar (dca) TOOLS BIOLOGISTS MAY USE TO ANALIZE THEIR EXPERIMENTAL DATA: LESSON 3. ? HOw TO USE ANALYSIS OF VARIANCE IN SOME COMMON CASES? ANOVA FOR A COMPLETELY RANDOM DESIGN (CRD) lo Que los biologos Pueden usar Para analiZar sus datos eXPerimentales: lección 3: ¿como usar análisis de varianZa Para algunos casos comunes? Nueva Granada. Available at: https://revistas.unimilitar.edu.co/index.php/rfcb/article/view/2240/1947?time=1722522769 (Accessed: 17 April 2025).
Casillas, M.Á. et al. (2021) Representaciones sociales, educación y análisis cualitativo con IRaMuTeQ Dirección Editorial. Available at: https://benv.edu.mx/wp-content/uploads/2023/10/Representaciones-sociales-IRaMuTeQ.pdf#page=23 (Accessed: 21 April 2025).
Huertas-García, R. et al. (2016) ‘Effet de la conception conjointe sur l’aptitude cognitive et le rendement. Une proposition de conception basée sur des blocs incomplets équilibrés’, Innovar, 26(59), pp. 73–90. Available at: https://doi.org/10.15446/innovar.v26n59.54325.
JOSÉ ANTONIO MONTILLA MARTOS (2023) INTELIGENCIA ARTIFICIAL Y DERECHOS DE PARTICIPACIÓN POLÍTICA. Available at: https://doi.org/https://doi.org/10.30827/dlf.1.2023.28552.
Kan, S. et al. (2022) ‘Contrastive Bayesian Analysis for Deep Metric Learning’. Available at: http://arxiv.org/abs/2210.04402.
Krishna, C.S. and Anoop, V.S. (2023) ‘Figurative Health-mention Classification from Social Media using Graph Convolutional Networks’, in 9th International Conference on Smart Computing and Communications: Intelligent Technologies and Applications, ICSCC 2023. Institute of Electrical and Electronics Engineers Inc., pp. 570–575. Available at: https://doi.org/10.1109/ICSCC59169.2023.10334990.
Marques Filho, E.G. et al. (2025) ‘O direito constitucional à proteção de dados e o tratamento dos dados pessoais: análise lexical da Política de Privacidade do TikTok a partir do software Iramuteq’, Revista Direito e Práxis, 16(2). Available at: https://doi.org/10.1590/2179-8966/2025/80645.
Nigam, H. and Biswas, P. (2021) ‘Web Scraping: From Tools to Related Legislation and Implementation Using Python’, in, pp. 149–164. Available at: https://doi.org/10.1007/978-981-15-9651-3_13.
RADUÁN LLOPIS, V. (2024) ‘TFG_VICTORIA RADUAN’. Available at: https://titula.universidadeuropea.com/bitstream/handle/20.500.12880/8876/TFG_VICTORIA%20RADUAN.pdf?sequence=1 (Accessed: 17 April 2025).
Rasuman, M.A. et al. (2024) ‘Trends and Networks in Education for Sustainable Development (ESD)… | 110’, Indonesian Journal of Multidisciplinary Research, 4(1), pp. 109–126. Available at: https://doi.org/10.17509/xxxx.xxx.
Ricardo Flores, Ml tlachac and Elke A. Rundenteiner (2022) ‘Measuring the Uncertainty of Environmental Good Preferences with Bayesian Deep Learning’.
Rostami-Tabar, B. et al. (2022) ‘Forecasting for social good’, International Journal of Forecasting, 38(3), pp. 1245–1257. Available at: https://doi.org/10.1016/j.ijforecast.2021.02.010.
Thivaharan., S., Srivatsun., G. and Sarathambekai., S. (2020) ‘A Survey on Python Libraries Used for Social Media Content Scraping’, in 2020 International Conference on Smart Electronics and Communication (ICOSEC). IEEE, pp. 361–366. Available at: https://doi.org/10.1109/ICOSEC49089.2020.9215357.
Thomas, D.M. and Mathur, S. (2019) ‘Data Analysis by Web Scraping using Python’, in 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA). IEEE, pp. 450–454. Available at: https://doi.org/10.1109/ICECA.2019.8822022.
Viudes Fernández, F.J. (2023) ‘Revolucionando la política: El papel omnipresente de la IA en la segmentación y el targeting de campañas modernas’, Más Poder Local, (53), pp. 146–151. Available at: https://doi.org/10.56151/maspoderlocal.183.
Xiong, F. et al. (2023) ‘A new adaptive multi-fidelity metamodel method using meta-learning and Bayesian deep learning’, Structural and Multidisciplinary Optimization, 66(3). Available at: https://doi.org/10.1007/s00158-023-03518-8.
Zhang, L. et al. (2021) ‘Extending Bayesian Learning to Intelligent Learning in Human Way’, in Procedia Computer Science. Elsevier B.V., pp. 118–124. Available at: https://doi.org/10.1016/j.procs.2022.01.015.
How to Cite
Downloads
Downloads
Published
Proceeding
Section
License
Copyright (c) 2025 Asociación Colombiana de Facultades de Ingeniería - ACOFI
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
| Article metrics | |
|---|---|
| Abstract views | |
| Galley vies | |
| PDF Views | |
| HTML views | |
| Other views | |
