Mediante una revisión crítica de los métodos convencionales de análisis de los materiales cualitativos, que suelen basarse en esquemas de codificación lineal y deductiva, propongo una alternativa metodológica basada en la asistencia de herramientas y modelos de inteligencia artificial (IA) para demostrar las ventajas interpretativas para las ciencias sociales a través del uso de topografías múltiples del discurso. En efecto, puede no ser una novedad el uso en la asistencia de la IA aplicada al análisis cualitativo; sin embargo, la alternativa que expongo debe su aporte en la codificación semántica y relacional, y no en la léxica-numérica. Así, el Modelo de Análisis de Resonancia Semántica Asistida (MARSA) no pierde de vista la importancia de la función revisora de la persona investigadora por lo que se aprovecha la interacción humana-tecnológica. En MARSA se contempla cinco fases. Inicia con la exploración, que se centra en la lectura inmersiva y flotante del corpus guiada por la reflexividad humana. La sistematización es la fase que ordena lógicamente la información en dimensiones operativas mediante el uso del lenguaje Python. La tercera etapa consiste en la extracción de nodos en los que se emplean modelos de IA para codificar los datos cualitativos de forma estructurada a partir de matrices. La cuarta fase refiere a la identificación de la resonancia de la interacción por medio de algoritmos de redes semánticas para generar gráficamente la conexión, proximidad y consolidación de los significados, superando el conteo léxico de las aplicaciones tradicionales. La interpretación humana es la fase final, en la que quien investiga retoma el liderazgo analítico para descifrar las cartografías visuales resultantes. Así, el modelo muestra la integración de herramientas algorítmicas y la IA para la sistematización de datos sin sacrificar la profundidad hermenéutica del sujeto cognoscente.
Through a critical review of conventional methods for analysing qualitative materials, which often rely on linear and deductive coding schemes, I propose a methodological alternative based on the assistance of artificial intelligence (AI) tools and models to demonstrate the interpretive advantages for the social sciences through the use of multiple discourse topographies. Indeed, the use of AI assistance applied to qualitative analysis may not be a novelty; however, the contribution of the alternative presented here lies in semantic and relational coding, rather than lexical-numerical coding. Thus, the Assisted Semantic Resonance Analysis Model (MARSA, by its acronym in Spanish) does not lose sight of the importance of the researcher's reviewing function, thereby leveraging human-technological interaction. MARSA comprises five phases. It begins with exploration, which focuses on an immersive and floating reading of the corpus guided by human reflexivity. Systematization is the phase that logically organizes the information into operational dimensions through the use of Python programming language. The third stage consists of node extraction, in which AI models are employed to code qualitative data in a structured manner using matrices. The fourth phase refers to identifying the resonance of interaction through semantic network algorithms to visually generate the connection, proximity, and consolidation of meanings, transcending the lexical counting of traditional applications. Human interpretation is the final phase, in which the researcher reclaims analytical leadership to decipher the resulting visual cartographies. Thus, the model demonstrates the integration of algorithmic tools and AI for data systematization without sacrificing the hermeneutic depth of the knowing subject.
Referencias
Bardin, L. (1996). Análisis de contenido. Akal.
Braun, V. y Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77-101. (2022). Toward good practice in thematic analysis: avoinding common problems and be(com)ing a knowing researcher. International Journal of Transgender Health, 24(1). DOI: https://doi.org/10.1080/26895269.2022.2129597.
Bryant, A. y Charmaz, K. (2007). The SAGE Handbook of Grounded Theory. SAGE.
Castilla Barraza, J. G., Cárdenas González, J. R. y La Rosa Huertas, L. del C. (2025). La complejidad humana en la investigación cualitativa como herramienta esecial de la investigación científica. Revista Científica en Ciencias Sociales, 7, 1-10. DOI: https://doi.org/10.53732/rccsociales/e701502.
Charmaz, K. (2006[2014]). Constructing Grounded Theory. SAGE.
Clarke, A. (2005). Situational Analysis: Grounded Theory After the Postmodern Turn. SAGE.
Costa, A. P., Bryda, G., Christou, P. A., y Kasperiuniene, J. (2025). AI as a Co-researcher in the Qualitative Research Workflow: Transforming Human-AI Collaboration. International Journal of Qualitative Methods, 24, 1-12. DOI: 10.1177/16094069251383739.
Denzin, N. y Lincoln, Y. (2000). The SAGE Handbook of Qualitative Research. SAGE.
Fairclough, N. (2003). Analyzing Discourse: Textual Analysis for Social Research. Routledge.
Glaser, B. y Strauss, A: (1967). The Grounded Theory: Strategies for Qualitative Research. Aldine.
Hamilton, L. (2023). Exploring the Use of AI in Qualitative Analysis: A Comparative Study of Guaranteed Income Data. International Journal of Qualitative Methods. DOI: https://doi.org/10.1177/16094069231201504.
Hiernaux, J. P. (1996). Análisis estructural de contenido y de modelos estructurales. Aplicación a materiales voluminosos. Universidad Católica de Lovaina.
Jackson, K., Paulus, T. y Woolf, N. H. (2018). The Walking Dead Genealogy: Unsubstantiated Criticisms of Qualitative Data Analysis Software (QDAS) and the Failure to Put Them to Rest. The Qualitative Report (TQR), 23 (13). DOI: https://doi.org/10.46743/2160-3715/2018.3096.
Kelle, U. (2007). "Emergence" vs. "forcing" of empirical data? A crucial problem of "Grounded Theory" reconsidered. Forum of Qualitative Social Research. URL: https://www.researchgate.net/publication/306174283_Emergence_vs_forcing_of_empirical_data_A_crucial_problem_of_Grounded_Theory_reconsidered
Krippendorff, K. (2019). Content Analysis: An Introduction to Its Methodology. SAGE.
Lincoln, Y. y Guba, E. G. (1985). Naturalistic Inquiry. SAGE.
Mayring, P. (2014). Qualitative content analysis. Forum Qualitative Sozialforschung, 1(2). URL: https://www.researchgate.net/publication/215666096_Qualitative_Content_Analysis
Morgan, D. L. (2023). Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT. International Journal of Qualitative Methods. DOI: https://doi.org/10.1177/16094069231211248.
Ngo, T. T., Nguyen Van, D., Nguyen, A.-M., Do, P.-A. y Nguyen-Quoc, A. (2026). Qualitative Coding Analysis through Open-Source Large Language Models: A User Study and Design Recommendations. arXiv:2602.18352. DOI: https://doi.org/10.48550/arXiv.2602.18352.
Nguyen-Trung, K. (2025). ChatGPT in thematic analysis: can AI become a research assistant in qualitative research? Quality & Quantity, 59(6), 4945-4978. DOI: https://doi.org/10.1007/s11135-025-02165-z. érez Serrano, G. (1994). Investigación cualitativa. Retos e interrogantes, I. Métodos. Editorial La Muralla.
Smith, J. A. (1996). Beyong the divide between cognition and discourse: using interpretative phenomenological analysis in health psychology. Psichology & Helath. 11, 126-271.
Smith, J. A., Flowers, P. y Larkin, M. (2009). Interpretative Phenomenological Analysis: Theory, Method and Research. SAGE.
Stough, L. M. y Lee, S. (2021). Grounded theory approaches used in educational research journals. International Journal of Qualitative Methods, 20, 1-13. DOI: 10.1177/16094069211052203.
Strauss, A. y Corbin, J. (1990). Basics of Qualitative Research: Grounded Theory Procedures and Techniques. SAGE.
Suárez, H. (2002). La sociología cualitativa: el método de análisis estructural de contenido. T’inkazos, 11, 53-68.
Topi, H., Valachi, J. S., Wright, R. T., Kaiser, K. Nunamaker, J. F., Sipior, J. C. y de Silva, G. (2010) IS 2010: Curriculum Guidelines for Undergraduate Degree Programs in Information Systems. AIS eLibrary.
Tuffour, I. (2017). A critical overview of Interpretative Phenomenological Analysis: a contemporary qualitative research approach. Journal of Healthcare Communications, 2(52).
Van Dijk, T. A. (2009). Discurso y poder. Gedisa. (2015). Ideology/Critical Discourse Analysis. En D. Tannen, H. E. Hamilton y D. Schiffrin (Eds.). The Handbook of Discourse Analysis (466-485). John Wiley & Sons, Inc.
Wen, S., Ku, B., Wang, T., Zou, M. y Yang, Y. (2025). Neo-Grounded Theory: A Methodological Innovation Integrating High-Dimensional Vector Clustering and Multi-Agent Collaboration for Qualitative Research. arXiv. DOI: https://doi.org/10.48550/arXiv.2509.25244.
Wodak, R. y Meyer, M. (2015). Methods of Critical Discourse Studies (3era edición). SAGE.
Xiao, Z., Yuan, X., Liao, Q. V., Abdelghani, R. y Oudeyer, P.-Y. (2023). Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding. arXiv:2304.10548.
Zhang, H., Wu, C., Xie, J., Rubino, F., Graver, S., Kim, C., Carroll, J. C. y Cai, J. (2024). When qualitative research meets large language model: exploring the potential of QualiGPT as a tool for qualitative coding. arXiv: 2407.14925.
Esta obra está bajo una Licencia Creative Commons Atribución-NoComercial-SinDerivadas 4.0 Internacional.