Artificial Intelligence in Textual Biographical Research: A Systematic Review of Methods, Effectiveness, and Epistemological Limits

Life Writing. 2026. Vol. 23. No. 3. P. 550–567.

Mikhaylova O.

Biographical research relies on rich life narratives but now faces scalability pressures as digital archives and clinical interview corpora expand. This systematic review synthesizes 56 empirical studies (2014–2025) that applied artificial intelligence or computational methods to textual biographical data, including oral histories, life history interviews, autobiographical narratives, clinical life stories, and memoirs. Studies were coded for methodological families, application domains, effectiveness, challenges, and gaps, and synthesized using qualitative content and thematic analysis. Applications clustered in six domains: narrative analysis, information extraction, disease and cognitive impairment classification, sentiment and emotion analysis, autobiographical memory scoring, and deception detection. Across 71 effectiveness findings, only 12.7% provided strong evidence, 4.2% reported mixed results, and 83.1% indicated limited or problematic effectiveness, especially for generalization, embedded deception detection, and nuanced narrative interpretation. The review concludes that AI currently functions best as an assistive tool for narrowly defined coding and extraction tasks and argues that hybrid human–AI workflows, stronger ethical frameworks, multilingual and multimodal expansion, and task-specific validation are essential for epistemically responsible use of AI in biographical research.

Keywords: autobiographical memory, narrative analysis, qualitative methods, biographical research, systematic review, Deception detection, ethics of AI, large language models, artificial intelligence, natural language processing