IEEE Transactions on Affective Computing Dataset Benchmark

PersoMoni

A Comprehensive Video-Based Benchmark Dataset for Fine-grained Personality Assessment with 5 Big Five Traits and 15 BFI-2 Sub-traits

Feng-Qi Cui1,2, Jinyang Huang1*, Sirui Zhao2, Kun Li3, Zhi Liu4, Meng Li1, Ziyu Jia5, Dan Guo1*, Meng Wang1

1 Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, School of Computer Science and Information Engineering, Hefei University of Technology

2 MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China

3 College of Information Technology, United Arab Emirates University

4 Department of Computer and Network Engineering, The University of Electro-Communications

5 Beijing Key Laboratory of Brainnetome and Brain-Computer Interface, Brainnetome Center, Institute of Automation, Chinese Academy of Sciences

* Corresponding authors

Paper Dataset Cite
168 Full-length Interviews
20K+ Face-aligned Clips
5+15 Big Five + BFI-2 Sub-traits
25 Avg. Minutes per Session

Clinically Grounded Personality Computing

Understanding personality from visual behavior remains challenging. Existing benchmarks rely on short, crowd-annotated clips and capture only coarse impressions, lacking temporal continuity, clinical validity, and fine-grained sub-trait structure.

PersoMoni overview: BFI-2 taxonomy, data collection pipeline, and dataset statistics
Figure 1. Overview of PersoMoni: (a) BFI-2 hierarchical structure with 5 major traits and 15 sub-traits; (b) guided psychological interview pipeline from recording to expert annotation; (c) dataset statistics and comparison with prior benchmarks.

Long-horizon Naturalistic Interaction

168 semi-structured interviews conducted by licensed counselors, eliciting authentic nonverbal cues across extended social interactions, not thin-slice impressions.

Expert-validated BFI-2 Labels

Continuous scores for all five Big Five domains and, for the first time in PTI benchmarks, fifteen validated BFI-2 sub-traits, scored independently by two psychology professionals.

Open Dataset for Research

A structured benchmark with interview videos, face-aligned clips, and expert BFI-2 annotations, to be released for academic research on fine-grained personality computing.

The PersoMoni Benchmark

PersoMoni bridges the gap between ecological validity and computational tractability, preserving the richness of full interviews while providing localized clip units for learning.

Collection Protocol

  • Semi-structured interviews with licensed psychological counselors on self-concept, relationships, and values
  • Pre-interview screening via SCL-90 and BFI-2 to tailor questioning
  • 1080p front-facing recording at 30 fps, seated natural posture, continuous eye contact
  • Face-centered processing via YOLO detection, temporal segmentation into clip units
  • Three-stage QC: individual scoring, cross-review, and consensus discussion

Key Properties

Participants168 (86 F / 82 M)
Video clips20,000+ face-aligned segments
Duration~25 min avg. per interview
Resolution1080p @ 30 fps
Label space20-dim continuous BFI-2 vector
AnnotationDual expert rating + averaging
DemographicsBalanced age & education groups
Prior benchmarks

Short clips | Crowd labels | 5 coarse traits | Thin-slice judgments

PersoMoni

Long interviews | Expert BFI-2 | 5 traits + 15 sub-traits | Ecologically valid

From 5 Traits to 15 Sub-traits

PersoMoni is the first personality computing benchmark to extend granularity from 5 to 15 dimensions, aligned with the psychometrically validated BFI-2 hierarchical framework.

Extraversion

  • Sociability
  • Assertiveness
  • Energy Level

Agreeableness

  • Compassion
  • Respectfulness
  • Trust

Conscientiousness

  • Organization
  • Productiveness
  • Responsibility

Negative Emotionality

  • Anxiety
  • Depression
  • Emotional Volatility

Open-Mindedness

  • Intellectual Curiosity
  • Aesthetic Sensitivity
  • Creative Imagination

How to Cite

If you use the PersoMoni dataset in your research, please cite our paper. 

@article{cui2026persomoni,
  author  = {Cui, Feng-Qi and Huang, Jinyang and Zhao, Sirui and Li, Kun and Liu, Zhi and Li, Meng and Jia, Ziyu and Guo, Dan and Wang, Meng},
  journal = {IEEE Transactions on Affective Computing},
  title   = {PersoMoni: A Comprehensive Video-Based Benchmark Dataset for Fine-grained Personality Assessment with 15 Trait Dimensions},
  year    = {2026},
  pages   = {1--14},
  doi     = {10.1109/TAFFC.2026.3698795},
  url     = {https://ieeexplore.ieee.org/document/11543185}
}