The use of Artificial Intelligence in Dream Research (Dream-AI)

funded by seed funding from the IPU Berlin

Principal Investigator IPU

Prof. Tamara Fischmann

Principal Investigator (external)

Dr. Michael Koslowski (Charité, Berlin)

Project Description

Dream-AI, a research project at the International Psychoanalytic University (IPU) Berlin, explores whether modern large language models (LLMs) such as GPT-4o, LLaMA, and Mistral can automate the analysis of dream reports. The project evaluates whether AI can reliably detect psychoanalytic indicators—such as primary and secondary process thinking(Primary Index, PI) and affect regulation and problem-solving capacity (Zurich Dream Process Coding System, ZDPCS)—and whether its assessments match those of trained human coders.

Using the open-access DreamBank database, AI-generated analyses are systematically compared to human ratings. The project is conducted in collaboration with international partners and supported by high-performance computing resources at Charité Berlin. Ultimately, Dream-AI aims to lay the foundation for a scalable AI-based tool to support both research and clinical applications in dream analysis.


Original Language: English (partially in German)

Participating Researchers

Dr. Christophe Bruno (Aix-Marseille University / ENS Paris)
Jacques Ehret, M.Sc. (Clinical Study Center, Charité Berlin)
Valeriu Lacatusu (Senior Machine Learning Engineer, Meta Paris)

Duration

Projekt Start: 03/2025
Projekt End: 12/2026