Doctoral research requires transforming heterogeneous evidence into defensible interpretations and decisions. In educational sciences this includes qualitative interpretation of interviews, documents and open responses, as well as quantitative analysis of survey, assessment and observational data. Generative AI can accelerate coding, summarization and exploratory pattern detection, but it also introduces epistemic, privacy, bias and reproducibility risks. The seminar therefore combines methodological foundations with hands-on use of free/open tools, emphasizing human judgment, audit trails, uncertainty, transparency and ethical AI use.
- Docente: Jesus Insuasti
The aim of this course is the application of hermeneutics supported by computational linguistics. This course introduces
planning and conducting qualitative data analysis with Computational linguistics. In this course, we will practice how
Computational linguistics accommodates and assists analysis across a wide range of research questions and data types.
Perspectives and methodologies. Some studied aspects will be:
• Flexibility in data types
• Assistance in each stage in a research project
• The usage of various tools in Computational linguistics for analyzing qualitative information.
• The use of visual representation of educational practices based on computational linguistics.
We will focus on visualizing data, working in mixed methods and social media datasets, and approaching Computational
linguistics as a team; in addition, we will use ESSENTIA CURRICULUM for representing practices in curriculum design.
- Docente: Jesus Insuasti