EUVIMEDEUVIMED entdecken
Crossref

From Traits to Configurations: An AI-Supported Methodology for Mapping Psychological Configurations Across Life Narratives

Keren Hazdai

Medical Research Archives · 2026

DOI: 10.18103/mra.2026.0726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Research Archives, 2026. Verfasst von Keren Hazdai.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Life narratives contain rich information about how psychological characteristics are expressed at different stages of a person’s life. Turning this complex narrative material into a systematic psychological representation that can be compared within the same person across a biographical sequence remains a methodological challenge.

Objective

This study examined an AI-supported method for identifying psychological configurations in life narratives and comparing them across different stages of the same person’s life.

Methods

We analyzed in-depth interviews with 13 former members of criminal organizations who subsequently became state witnesses. Each narrative was divided into 10 biographical stages. Each stage was coded separately by a large language model (LLM) using a predefined theoretical framework comprising the 25 PID-5 personality facets. The model was not given access to configurations generated from other stages. The resulting configurations were compared within individuals across the peak of their criminal careers, subsequent crises, and the stage at which crossing lines of loyalty emerged.

Results

The degree of overlap between the peak-career configuration and configurations from earlier crisis stages varied considerably across participants. In contrast, at the stage of crossing lines of loyalty, all 13 participants showed low overlap with their peak-career configuration (Jaccard ≤0.25). The relative composition of the configurations also differed across stages. Grandiosity and Risk Taking were more frequently represented at the peak of the criminal career, whereas Anxiousness, Depressivity, and Suspiciousness were more frequently represented at the stage of crossing lines of loyalty.

Conclusion

The findings show that an LLM operating within a predefined psychological framework can be used to systematically code life narratives and generate multidimensional configurations that can be compared within the same individual across biographical stages. This approach extends AI-supported psychological analysis beyond the assessment of individual characteristics at a single point in time to the examination of configurations across a biographical sequence. The findings concern psychological configurations as represented and coded in the narratives and provide a methodological basis for studying intraindividual variation in complex biographical processes.

Zitieren

APA

Hazdai, K. (2026). From Traits to Configurations: An AI-Supported Methodology for Mapping Psychological Configurations Across Life Narratives. Medical Research Archives. https://doi.org/10.18103/mra.2026.0726

Vancouver

Hazdai K. From Traits to Configurations: An AI-Supported Methodology for Mapping Psychological Configurations Across Life Narratives. Medical Research Archives. 2026. doi:10.18103/mra.2026.0726

BibTeX
@article{Hazdai2026,
  author = {Hazdai, Keren},
  title = {From Traits to Configurations: An AI-Supported Methodology for Mapping Psychological Configurations Across Life Narratives},
  journal = {Medical Research Archives},
  year = {2026},
  doi = {10.18103/mra.2026.0726}
}
Kostenlos starten →