An End-to-End Workflow for Processing Multilingual Stakeholder Workshop Data: A Soil Health Case Study

Vid Podpečan, Bojan Blažica, Fabio Volkmann, Carmen Vazquez Martin, Rachel Creamer, Marko Debeljak

Stakeholder workshops often produce diverse qualitative and ordinal data that are difficult to process consistently, transparently, and reproducibly, particularly in multilingual settings. To address these challenges, we developed an end-to-end workflow for systematic processing of multilingual participatory workshop data. The workflow integrates multilingual preprocessing, structured data management, computational analysis, automated reporting, and interactive dissemination. It incorporates a range of data analysis methods, including large language models. The workflow supports both qualitative exploration and quantitative comparison of stakeholder perspectives across workshops and contexts. We also propose a structured approach based on large language models for topic extraction and intensity scoring, which transforms qualitative workshop inputs into comparable quantitative representations of obtained results. The proposed workflow is demonstrated in the EU BENCHMARKS project, which involves multiple workshops, stakeholder groups, land-use contexts, and languages. The main contribution of this work is a transparent, reproducible, and adaptable workflow for the systematic handling of multilingual participatory workshop data that supports reproducible analysis, scalable dissemination, and cross-workshop comparison.