Research

LaclauGPT is an open social-science research framework for LLM-assisted computational discourse analysis of large textual and multimodal corpora. It combines computational methods with interpretive political research while keeping model outputs traceable to source evidence, uncertainty, provenance, and human review.

LaclauGPT has been under development by Tomi Toivio since 2023. Contact: tomi.toivio@helsinki.fi.

The framework originated in the EP24 research project, connected with the Helsinki Hub on Emotions, Populism and Polarisation (HEPP) and the Helsinki Institute for Social Sciences and Humanities (HSSH). The present version is guided primarily by the AI26 research project, together with other ongoing research projects and methodological work.

The current flagship programme is LaclauGPT: Ideological contestation over AI.

The framework is grounded in discourse theory associated with Ernesto Laclau and Chantal Mouffe, with computational and LLM-assisted extensions designed for human-in-the-loop social-science research.

Core research documents

• Theory and methodology
• Phase 1 scientific paper
• Roadmap
• Validation protocol
• Confidence and uncertainty

Research-use boundary

Human-in-the-loop academic research only. Machine-generated interpretations are preliminary analytical proposals. Source evidence and interpretations must be verified by a human researcher before they are reported or cited as research conclusions.