Machine-Learning Decomposition Identifies a Big Two Structure in Human Personality with Distinct Neurocognitive Profiles.

Overview

1. Institute of Science and Technology for Brain‐Inspired Intelligence, Fudan University, Shanghai, China
2. Center for Brain Health and Brain Technology, Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China
3. School of Psychology, Southwest University, Chongqing, China
4. Institute of Neuroscience and Medicine, Brain and Behaviour (INM‐7), Research Center Jülich, Jülich, Germany
5. Institute of Systems Neuroscience, Medical Faculty, Heinrich Heine University Düsseldorf, Düsseldorf, Germany

Abstract

Personality neuroscience has traditionally relied on the Big Five model to investigate trait structure and its relationship to individual differences in brain organization and life outcomes. However, existing theoretical frameworks explain only part of the item‐level covariance, raising questions about whether alternative factor solutions might complement the canonical five‐factor model. Here, we applied an additive and part‐based machine learning decomposition to a mega‐scale, global dataset (n = 1,336,840) to systematically evaluate trait structure across factor resolutions. Beyond reproducing the canonical Big Five, we identified a robust Big Two comprising Social Adaptation and Spontaneous Mentation. Social Adaptation integrates covarying questionnaire items from Extraversion, Agreeableness, and Conscientiousness, indexing externally oriented social functioning. Spontaneous Mentation, in turn, aggregates Neuroticism with introspective facets of Openness, capturing internally directed affective‐cognitive exploration. Embedding individuals in this Big Two space revealed structured manifolds along which neurocognitive profiles aligned with distinct trait orientations. Importantly, this lower‐dimensional representation improved prediction of functional brain connectivity relative to Big Five scores, while preserving comparable associations with cognition and mental health. Together, these results establish a neurocognitively grounded Big Two framework that complements the Big Five and offers an interpretable bridge between personality structure, cognitive functioning, and psychopathology.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• dataverse.harvard.edu/dataverse/escs-data, at dataverse.harvard.edu; found in “Data Availability Statement”
• osf:tbmh5, at OSF; found in “Data Availability Statement”

Data Availability Statement

The IPIP‐120 and IPIP‐300 inventories are constructed from IPIP items, and the response datasets analyzed in this study are publicly available from Johnson's OSF repository (https://osf.io/tbmh5/). NEO‐FFI questionnaire data, domain‐based behavior data, and neuroimage data obtained from the HCP datasets are publicly available at https://www.humanconnectome.org/. NEO‐PI‐R questionnaire data from the ESCS dataset is available at https://dataverse.harvard.edu/dataverse/ESCS‐Data (https://dataverse.harvard.edu/dataverse/ESCS-Data). The BBC data is available at https://beta.ukdataservice.ac.uk/datacatalogue/doi/?id=7656#!#1.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 8 authors, 4 keywords, 8 MeSH terms, 3 funders, 53 references.

Cite

This paper

Zhuang, K., Chen, J., Han, J., Cheng, W., Qiu, J., Feng, J., Eickhoff, S., & Vatansever, D. (2026). Machine-Learning Decomposition Identifies a Big Two Structure in Human Personality with Distinct Neurocognitive Profiles. Advanced science (Weinheim, Baden-Wurttemberg, Germany), 13(28), e09009. https://doi.org/10.1002/advs.202509009

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-026-75841-9 [code]

Model-based semantic distance reveals adaptive coordination of distinct cognitive systems in flexible knowledge retrieval.

Journal: Nature communications

In common: cognitive, 5 references, 2 authors

[2] doi:10.1038/s41467-026-73153-6 [code]

Latent neural architecture organising shared aesthetic evaluations of visual artworks.

Journal: Nature communications

In common: cognitive, 7 references, 2 authors

[3] doi:10.1038/s42003-025-08151-3 [code]

Functional divergence between the two cerebral hemispheres contributes to human fluid intelligence.

Journal: Communications biology

In common: 6 references, author Deniz Vatansever

[4] doi:10.1371/journal.pbio.3003399 [code]

Identification of five sleep-biopsychosocial profiles with specific neural signatures linking sleep variability with health, cognition, and lifestyle factors.

Journal: PLoS biology

In common: cognitive, 10 references

[5] doi:10.1038/s42003-025-07470-9 [code]

Dynamic switching between brain networks predicts creative ability.

Journal: Communications biology

In common: cognitive, 3 references, author Kaixiang Zhuang

[6] doi:10.1038/s41467-025-63661-2 [code]

Motion impact score for detecting spurious brain-behavior associations.

Journal: Nature communications

In common: 9 references

[7] doi:10.1126/sciadv.adu5251 [code]

Neural representations of noncentral events during narrative encoding predict subsequent story ending originality.

Journal: Science advances

In common: 3 references, author Kaixiang Zhuang

[8] doi:10.1002/hbm.26517 [code]

Test-retest reliability and predictive utility of a macroscale principal functional connectivity gradient.

Journal: Human brain mapping

In common: 8 references

[9] doi:10.1002/hbm.26683 [code]

Sex classification from functional brain connectivity: Generalization to multiple datasets.

Journal: Human brain mapping

In common: 7 references

[10] doi:10.1016/j.neuroimage.2023.119972 [code]

Less is more: balancing noise reduction and data retention in fMRI with data-driven scrubbing.

Journal: NeuroImage

In common: 8 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.