pith. sign in

arxiv: 2606.29900 · v1 · pith:FUVZGS3Enew · submitted 2026-06-29 · 💻 cs.CV · cs.AI

LLM-based Multimodal Personality Recognition via Facial Action Unit-Text Semantic Fusion

Tianyi Zhang , Wei Shan , Yuan Zong , Tianhua Qi , Wenming Zheng This is my paper

Pith reviewed 2026-06-30 06:23 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords personality recognitionfacial action unitslarge language modelsmultimodal fusionasynchronous video interviewssemantic fusionAVI-6 benchmarkregression head
0
0 comments X

The pith

Converting facial action units to text and fusing them with interview responses in an LLM improves personality score prediction.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that turning sequences of facial action units into readable text descriptions, then combining those descriptions with an interviewee's spoken responses inside a large language model, produces more accurate continuous personality trait scores than text-only or image-based multimodal baselines. This matters because existing methods either ignore facial cues entirely or lose the fine timing of expressions when using full frames. The fusion step lets the model treat non-verbal signals as semantic content that complements verbal answers, after which a small regression layer maps the combined embeddings to trait scores. On the AVI-6 benchmark the approach yields lower prediction errors and higher correlations with human ratings across traits. The separation of semantic fusion from the final regression also improves training stability.

Core claim

The paper claims that an LLM-based framework converts AU sequences into interpretable textual descriptions, fuses those descriptions with participants' textual responses through the LLM, and passes the resulting embeddings through a lightweight regression head to obtain continuous personality scores; this produces lower prediction errors and stronger correlations with human-rated scores than most baselines on the AVI-6 benchmark while supplying complementary non-verbal cues and greater training stability.

What carries the argument

Semantic fusion inside an LLM of AU-derived textual descriptions with interviewee text responses, followed by a regression head on the embeddings.

If this is right

  • The fused representations supply complementary non-verbal information that text responses alone miss.
  • Prediction errors drop and correlations with human ratings rise across multiple personality traits.
  • Decoupling semantic understanding from the regression step increases training stability.
  • The method remains computationally lighter than approaches that feed full face images or dense frame sequences into the model.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same AU-to-text conversion step could be tested on other video-based affective tasks such as emotion or engagement detection.
  • Replacing the current LLM with smaller or open-source models might preserve most gains while lowering compute cost.
  • Collecting new AVI datasets that vary interview length or lighting would show whether the textual AU descriptions remain robust.

Load-bearing premise

Turning sequences of facial action units into textual descriptions keeps the fine-grained timing and intensity information that matters for personality assessment without major loss.

What would settle it

A controlled test on AVI-6 that replaces the AU-to-text step with either raw AU numeric features or full video frames and measures whether prediction error and correlation with human scores stop improving or worsen.

Figures

Figures reproduced from arXiv: 2606.29900 by Tianhua Qi, Tianyi Zhang, Wei Shan, Wenming Zheng, Yuan Zong.

Figure 1
Figure 1. Figure 1: Overview of the proposed multimodal personality assessment framework, consisting of four components: (a) Preprocessing, (b) Facial action unit [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Structured prompt design for generating semantic descriptions of AU [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Structured prompt design for generating global summary descriptions [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Structured prompt design for generating embeddings for personality [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: MSE Comparison Across Personality Traits [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Mismatch Between LSTM Optimization and Final Performance [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: Frequency distributions of predicted personality scores by our method [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 7
Figure 7. Figure 7: Frequency distributions of predicted personality scores by zero-shot [PITH_FULL_IMAGE:figures/full_fig_p014_7.png] view at source ↗
read the original abstract

Personality recognition in asynchronous video interviews (AVIs) has become increasingly important due to their widespread adoption in modern recruitment. Existing approaches often rely on large language models (LLMs) to analyze textual responses of interviewees in AVI. However, unimodel methods often suffer from information loss (e.g., ignore facial cues). In contrast, multimodal methods that employ full-face images or sparsely sampled frames can discard fine-grained temporal dynamics critical for accurate personality assessment. To overcome these limitations, we propose an LLM-based framework that semantically fuse facial action units (AUs) with textual responses of AVI. AU sequences are first converted into interpretable textual descriptions, which are then fused with participants' textual responses through an LLM. A lightweight regression head transforms the resulting embeddings into continuous personality scores without disrupting the underlying semantic space. Experiments on the AVI-6 benchmark demonstrate consistent improvements over most baselines, with lower prediction errors and stronger correlations with human-rated scores across multiple traits. Further analysis reveals that AU-derived semantic representations offer complementary non-verbal cues to textual responses. Decoupling semantic understanding from regression prediction within the LLM also leads to greater training stability and clearer interpretability. Overall, these findings demonstrate that AU-text fusion provides a psychologically grounded and computationally efficient framework for personality recognition in AVIs.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes an LLM-based multimodal framework for personality recognition in asynchronous video interviews (AVIs). Facial action unit (AU) sequences are converted into textual descriptions that are then semantically fused with interviewees' textual responses via an LLM; a lightweight regression head maps the resulting embeddings to continuous personality trait scores. The central claim is that this AU-text fusion yields lower prediction errors and stronger correlations with human ratings than baselines on the AVI-6 benchmark, while supplying complementary non-verbal cues and improved training stability.

Significance. If the empirical claims hold with proper validation, the work would demonstrate a computationally lightweight route to incorporating non-verbal facial dynamics into LLM pipelines without full-frame video processing. The design choice to decouple semantic fusion from regression is a clear strength for interpretability.

major comments (2)
  1. [§3] §3 (Method): The AU-to-text conversion step is described only at a high level as producing 'interpretable textual descriptions.' No details are supplied on the encoding of temporal structure (onset/offset timing, intensity trajectories, or co-occurrence patterns), making it impossible to assess whether fine-grained sequential information is retained or collapsed into static summaries.
  2. [§4] §4 (Experiments): The abstract and results section assert 'consistent improvements over most baselines' with 'lower prediction errors and stronger correlations' on AVI-6, yet supply no numerical values, baseline identities, error metrics (e.g., MAE, RMSE), correlation coefficients, error bars, statistical tests, or ablation studies. This absence renders the central performance claim unevaluable.
minor comments (2)
  1. [Abstract] The AVI-6 benchmark is referenced without a citation or brief description of its traits, size, or annotation protocol.
  2. [§3] Notation for personality traits and AU indices is introduced without an explicit table or legend.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the two major comments below and will revise the manuscript accordingly to improve clarity and completeness.

read point-by-point responses

  1. Referee: [§3] §3 (Method): The AU-to-text conversion step is described only at a high level as producing 'interpretable textual descriptions.' No details are supplied on the encoding of temporal structure (onset/offset timing, intensity trajectories, or co-occurrence patterns), making it impossible to assess whether fine-grained sequential information is retained or collapsed into static summaries.

    Authors: We agree that Section 3 currently describes the AU-to-text conversion at a high level. In the revised manuscript we will expand this section with explicit details on the encoding procedure, including how onset/offset timing, intensity values, and co-occurrence patterns are represented in the generated textual descriptions to retain sequential information. revision: yes

  2. Referee: [§4] §4 (Experiments): The abstract and results section assert 'consistent improvements over most baselines' with 'lower prediction errors and stronger correlations' on AVI-6, yet supply no numerical values, baseline identities, error metrics (e.g., MAE, RMSE), correlation coefficients, error bars, statistical tests, or ablation studies. This absence renders the central performance claim unevaluable.

    Authors: The current manuscript version indeed omits specific numerical results, baseline names, exact metrics, error bars, and statistical tests from both the abstract and the results overview. We will revise the abstract and Section 4 to include these quantitative details (MAE, RMSE, Pearson/Spearman correlations, error bars, p-values where applicable) along with the identities of the baselines and a summary of the ablation studies. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation is self-contained

full rationale

The provided abstract and description contain no equations, parameter-fitting steps, or self-citations that reduce any claimed prediction or result to its own inputs by construction. The framework converts AU sequences to text then fuses via LLM before regression; this is presented as a standard pipeline evaluated empirically on AVI-6 without self-definitional loops, fitted-input predictions, or load-bearing self-citations. The central claims rest on external benchmark performance rather than internal redefinition, qualifying as a normal non-circular finding.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies insufficient technical detail to enumerate free parameters, axioms, or invented entities; no equations, fitting procedures, or new constructs are described.

pith-pipeline@v0.9.1-grok · 5760 in / 1146 out tokens · 26584 ms · 2026-06-30T06:23:00.708343+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

134 extracted references · 23 canonical work pages · 10 internal anchors

  1. [1]

    , title =

    Diener, Edward and Lucas, Richard E. , title =. General Psychology: Required Reading , editor =. 2019 , publisher =

    2019

  2. [2]

    and Whiteman, Michelle C

    Matthews, Gerald and Deary, Ian J. and Whiteman, Michelle C. , title =. 2003 , publisher =

    2003

  3. [3]

    2023 , issue_date =

    Liu, Zhiyuan and Xu, Wei and Zhang, Wenping and Jiang, Qiqi , title =. 2023 , issue_date =. doi:10.1016/j.ipm.2022.103256 , journal =

    work page doi:10.1016/j.ipm.2022.103256 2023

  4. [4]

    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops , year =

    Kaya, Huseyin and Gurpinar, Fatih and Ali Salah, Ahmed , title =. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops , year =

  5. [5]

    2024 , eprint=

    Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation , author=. 2024 , eprint=

    2024

  6. [6]

    invisible hand

    Deposit AI as the “invisible hand” to make the resale easier: A moderated mediation model , author=. Journal of Retailing and Consumer Services , volume=. 2023 , publisher=

    2023

  7. [7]

    2023 , eprint=

    Is ChatGPT a Good Personality Recognizer? A Preliminary Study , author=. 2023 , eprint=

    2023

  8. [8]

    , author=

    Decoding discrepant nonverbal cues. , author=. Journal of Personality and Social Psychology , volume=. 1978 , publisher=

    1978

  9. [9]

    , address =

    Hirschmüller, Sarah and Egloff, Boris and Nestler, Steffen and Back, Mitja D. , address =. The Dual Lens Model: A Comprehensive Framework for Understanding Self-Other Agreement of Personality Judgments at Zero Acquaintance , volume =. Journal of personality and social psychology , keywords =. 2013 , issn =

    2013

  10. [10]

    Thin Slices of Expressive Behavior as Predictors of Interpersonal Consequences: A Meta-Analysis , volume =

    Ambady, Nalini and Rosenthal, Robert , address =. Thin Slices of Expressive Behavior as Predictors of Interpersonal Consequences: A Meta-Analysis , volume =. Psychological bulletin , keywords =. 1992 , issn =

    1992

  11. [11]

    International Journal of Computer Vision , volume=

    Cr-net: A deep classification-regression network for multimodal apparent personality analysis , author=. International Journal of Computer Vision , volume=. 2020 , publisher=

    2020

  12. [12]

    Deep Bimodal Regression of Apparent Personality Traits from Short Video Sequences , year=

    Wei, Xiu-Shen and Zhang, Chen-Lin and Zhang, Hao and Wu, Jianxin , journal=. Deep Bimodal Regression of Apparent Personality Traits from Short Video Sequences , year=

  13. [13]

    MPRNet: a Temporal-Aware Cross-Modal Encoding Framework for Personality Recognition , year=

    Li, Jian and Zhang, Huawei and Chen, Junyi and Gong, Junhui and Wang, Yufan and Wang, Shifeng and Zhao, Yuliang , journal=. MPRNet: a Temporal-Aware Cross-Modal Encoding Framework for Personality Recognition , year=

  14. [14]

    Multimodal Co-attention Transformer for Video-Based Personality Understanding , year=

    Sun, Mingwei and Zhang, Kunpeng , booktitle=. Multimodal Co-attention Transformer for Video-Based Personality Understanding , year=

  15. [15]

    Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement prediction , journal =

    Ming Li and Xiaosheng Zhuang and Lu Bai and Weiping Ding , keywords =. Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement prediction , journal =. 2024 , issn =. doi:https://doi.org/10.1016/j.inffus.2024.102224 , url =

    work page doi:10.1016/j.inffus.2024.102224 2024

  16. [16]

    2023 , eprint=

    The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) , author=. 2023 , eprint=

    2023

  17. [17]

    2023 , eprint=

    Visual Instruction Tuning , author=. 2023 , eprint=

    2023

  18. [20]

    Current Directions in Psychological Science , volume=

    Accurate personality judgment , author=. Current Directions in Psychological Science , volume=. 2012 , publisher=

    2012

  19. [21]

    Frontiers in Psychology , author=

    Asynchronous Video Interviewing as a New Technology in Personnel Selection: The Applicant’s Point of View , volume=. Frontiers in Psychology , author=. 2016 , month=. doi:10.3389/fpsyg.2016.00863 , abstractNote=

    work page doi:10.3389/fpsyg.2016.00863 2016

  20. [22]

    'Be Cool!': Emotional costs of hiding feelings in a job interview , volume =

    Sieverding, Monika , address =. 'Be Cool!': Emotional costs of hiding feelings in a job interview , volume =. International journal of selection and assessment , keywords =

  21. [23]

    and Powell, Deborah M

    Feiler, Amanda R. and Powell, Deborah M. , address =. Behavioral Expression of Job Interview Anxiety , volume =. Journal of business and psychology , keywords =

  22. [24]

    Ashton and Kibeom Lee , title =

    Michael C. Ashton and Kibeom Lee , title =. Personality and Social Psychology Review , volume =. 2007 , doi =

    2007

  23. [25]

    Comparative Validity of Brief to Medium-Length Big Five and Big Six Personality Questionnaires , volume =

    Thalmayer, Amber Gayle and Saucier, Gerard and Eigenhuis, Annemarie , address =. Comparative Validity of Brief to Medium-Length Big Five and Big Six Personality Questionnaires , volume =. Psychological assessment , keywords =. 2011 , issn =

    2011

  24. [26]

    Multimodal Self-Assessed Personality Estimation During Crowded Mingle Scenarios Using Wearables Devices and Cameras , year=

    Cabrera-Quiros, Laura and Gedik, Ekin and Hung, Hayley , journal=. Multimodal Self-Assessed Personality Estimation During Crowded Mingle Scenarios Using Wearables Devices and Cameras , year=

  25. [27]

    , address =

    Lee, Kibeom and Ashton, Michael C. , address =. The H factor of personality : why some people are manipulative, self-entitled, materialistic, and exploitive-- and why it matters for everyone , year =

  26. [28]

    Personality and Prosocial Behavior: A Theoretical Framework and Meta-Analysis , volume =

    Thielmann, Isabel and Spadaro, Giuliana and Balliet, Daniel , address =. Personality and Prosocial Behavior: A Theoretical Framework and Meta-Analysis , volume =. Psychological bulletin , keywords =. 2020 , issn =

    2020

  27. [29]

    Oostrom and Reinout E

    Jan Luca Pletzer and Margriet Bentvelzen and Janneke K. Oostrom and Reinout E. A meta-analysis of the relations between personality and workplace deviance: Big Five versus HEXACO , journal =. 2019 , issn =. doi:https://doi.org/10.1016/j.jvb.2019.04.004 , url =

    work page doi:10.1016/j.jvb.2019.04.004 2019

  28. [30]

    EURASIP Journal on Image and Video Processing , volume=

    Predicting the Sixteen Personality Factors (16PF) of an individual by analyzing facial features , author=. EURASIP Journal on Image and Video Processing , volume=. 2017 , publisher=

    2017

  29. [31]

    Frontiers in Public Health , volume=

    Identifying Big Five personality traits based on facial behavior analysis , author=. Frontiers in Public Health , volume=. 2022 , publisher=

    2022

  30. [32]

    Journal of Contemporary Behavioural and Social Research , language =

    Facial Action Units and Personality Traits: An Explorative Approach through Computer Vision , volume =. Journal of Contemporary Behavioural and Social Research , language =. 2025 , issn =

    2025

  31. [33]

    Self-Supervised Learning of Person-Specific Facial Dynamics for Automatic Personality Recognition , year=

    Song, Siyang and Jaiswal, Shashank and Sanchez, Enrique and Tzimiropoulos, Georgios and Shen, Linlin and Valstar, Michel , journal=. Self-Supervised Learning of Person-Specific Facial Dynamics for Automatic Personality Recognition , year=

  32. [34]

    A Personality Trait-Based Interactionist Model of Job Performance , volume =

    Tett, Robert P and Burnett, Dawn D , address =. A Personality Trait-Based Interactionist Model of Job Performance , volume =. Journal of applied psychology , keywords =

  33. [35]

    and King, Laura A

    Pennebaker, James W. and King, Laura A. , title =. 1999 , journal =. doi:10.1037/0022-3514.77.6.1296 , type =

    work page doi:10.1037/0022-3514.77.6.1296 1999

  34. [36]

    2020 , eprint=

    Language Models are Few-Shot Learners , author=. 2020 , eprint=

    2020

  35. [37]

    2023 , eprint=

    Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , author=. 2023 , eprint=

    2023

  36. [38]

    2024 , eprint=

    Gemma: Open Models Based on Gemini Research and Technology , author=. 2024 , eprint=

    2024

  37. [39]

    2023 , eprint=

    Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation , author=. 2023 , eprint=

    2023

  38. [40]

    2023 , eprint=

    PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection , author=. 2023 , eprint=

    2023

  39. [41]

    and Holtrop, Djurre and Ghassemi, Sina and de Vries, Reinout E

    Zhang, Tianyi and Koutsoumpis, Antonis and Oostrom, Janneke K. and Holtrop, Djurre and Ghassemi, Sina and de Vries, Reinout E. , journal=. Can Large Language Models Assess Personality From Asynchronous Video Interviews? A Comprehensive Evaluation of Validity, Reliability, Fairness, and Rating Patterns , year=

  40. [42]

    Computer Animation and Virtual Worlds , volume=

    Adaptive information fusion network for multi-modal personality recognition , author=. Computer Animation and Virtual Worlds , volume=. 2024 , publisher=

    2024

  41. [43]

    Multimodal Automatic Personality Perception Using ViT, BiLSTM and VGGish , year=

    Duan, Xiaodong and Li, Haoyong and Yang, Feng and Chen, Bo and Dong, Jingshuai and Wang, Yuangang , booktitle=. Multimodal Automatic Personality Perception Using ViT, BiLSTM and VGGish , year=

  42. [44]

    Automated Scoring of Asynchronous Interview Videos Based on Multi-Modal Window-Consistency Fusion , year=

    Lv, Jianming and Chen, Chujie and Liang, Zequan , journal=. Automated Scoring of Asynchronous Interview Videos Based on Multi-Modal Window-Consistency Fusion , year=

  43. [45]

    Environmental Psychology & Nonverbal Behavior , year=

    Facial action coding system , author=. Environmental Psychology & Nonverbal Behavior , year=

  44. [46]

    OpenFace: An open source facial behavior analysis toolkit , year=

    Baltrušaitis, Tadas and Robinson, Peter and Morency, Louis-Philippe , booktitle=. OpenFace: An open source facial behavior analysis toolkit , year=

  45. [47]

    An Open-Source Benchmark of Deep Learning Models for Audio-Visual Apparent and Self-Reported Personality Recognition , year=

    Liao, Rongfan and Song, Siyang and Gunes, Hatice , journal=. An Open-Source Benchmark of Deep Learning Models for Audio-Visual Apparent and Self-Reported Personality Recognition , year=

  46. [48]

    Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection , year=

    Yang, Huiyuan and Yin, Lijun and Zhou, Yi and Gu, Jiuxiang , booktitle=. Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection , year=

  47. [49]

    2025 , eprint=

    Understanding LLM Embeddings for Regression , author=. 2025 , eprint=

    2025

  48. [50]

    Proceedings of the 33rd ACM International Conference on Multimedia , pages=

    Assessing Personality Traits and Interview Performance from Asynchronous Video Interviews , author=. Proceedings of the 33rd ACM International Conference on Multimedia , pages=

  49. [51]

    Long Short-Term Memory , year=

    Hochreiter, Sepp and Schmidhuber, Jürgen , journal=. Long Short-Term Memory , year=

  50. [52]

    Deep Residual Learning for Image Recognition , year=

    He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian , booktitle=. Deep Residual Learning for Image Recognition , year=

  51. [53]

    2021 , eprint=

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale , author=. 2021 , eprint=

    2021

  52. [54]

    2020 , eprint=

    Longformer: The Long-Document Transformer , author=. 2020 , eprint=

    2020

  53. [55]

    2019 , eprint=

    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , author=. 2019 , eprint=

    2019

  54. [56]

    2025 , eprint=

    Qwen3 Technical Report , author=. 2025 , eprint=

    2025

  55. [57]

    New York: Guilford Publications , pages=

    Facial expression of emotion , author=. New York: Guilford Publications , pages=

  56. [58]

    , author=

    Influence of extraversion and neuroticism on subjective well-being: happy and unhappy people. , author=. Journal of personality and social psychology , volume=. 1980 , publisher=

    1980

  57. [59]

    , TITLE=

    Gothard, Katalin M. , TITLE=. Frontiers in Neuroscience , VOLUME=. 2014 , URL=. doi:10.3389/fnins.2014.00043 , ISSN=

    work page doi:10.3389/fnins.2014.00043 2014

  58. [60]

    The Duchenne Smile: Emotional Expression and Brain Physiology II , volume =

    Ekman, Paul and Davidson, Richard J and Friesen, Wallace V , address =. The Duchenne Smile: Emotional Expression and Brain Physiology II , volume =. Journal of personality and social psychology , keywords =

  59. [61]

    Faces of Focus: A Study on the Facial Cues of Attentional States , year =

    Babaei, Ebrahim and Srivastava, Namrata and Newn, Joshua and Zhou, Qiushi and Dingler, Tilman and Velloso, Eduardo , address =. Faces of Focus: A Study on the Facial Cues of Attentional States , year =. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems , copyright =

    2020

  60. [62]

    Wingenbach, Tanja S. H. , title =. Social and Affective Neuroscience of Everyday Human Interaction: From Theory to Methodology , editor =. 2023 , pages =

    2023

  61. [63]

    and Fidell, Linda S

    Tabachnick, Barbara G. and Fidell, Linda S. , address =. Using multivariate statistics , year =. Using multivariate statistics , edition =

  62. [64]

    Investigation of the Relationships between Personality Traits and Self-Perceptions of Leadership Behaviors of Faculty of Sport Sciences Students , journal=

    Bulut, Adem and Karata. Investigation of the Relationships between Personality Traits and Self-Perceptions of Leadership Behaviors of Faculty of Sport Sciences Students , journal=. 2024 , DOI=

    2024

  63. [65]

    American Mathematical Society

    Mathematics Into Type . American Mathematical Society. [Online]. Available: https://www.ams.org/arc/styleguide/mit-2.pdf

  64. [66]

    T. W. Chaundy, P. R. Barrett and C. Batey, The Printing of Mathematics . London, U.K., Oxford Univ. Press, 1954

    1954

  65. [67]

    Mittelbach and M

    F. Mittelbach and M. Goossens, The Companion , 2nd ed. Boston, MA, USA: Pearson, 2004

    2004

  66. [68]

    Gr\"atzer, More Math Into LaTeX , New York, NY, USA: Springer, 2007

    G. Gr\"atzer, More Math Into LaTeX , New York, NY, USA: Springer, 2007

    2007

  67. [69]

    Letourneau and J

    M. Letourneau and J. W. Sharp, AMS-StyleGuide-online.pdf, American Mathematical Society, Providence, RI, USA, [Online]. Available: http://www.ams.org/arc/styleguide/index.html

  68. [70]

    Sira-Ramirez, ``On the sliding mode control of nonlinear systems,'' Syst

    H. Sira-Ramirez, ``On the sliding mode control of nonlinear systems,'' Syst. Control Lett., vol. 19, pp. 303--312, 1992

    1992

  69. [71]

    Levant, ``Exact differentiation of signals with unbounded higher derivatives,'' in Proc

    A. Levant, ``Exact differentiation of signals with unbounded higher derivatives,'' in Proc. 45th IEEE Conf. Decis. Control, San Diego, CA, USA, 2006, pp. 5585--5590. DOI: 10.1109/CDC.2006.377165

    work page doi:10.1109/cdc.2006.377165 2006

  70. [72]

    Fliess, C

    M. Fliess, C. Join, and H. Sira-Ramirez, ``Non-linear estimation is easy,'' Int. J. Model., Ident. Control, vol. 4, no. 1, pp. 12--27, 2008

    2008

  71. [73]

    Ortega, A

    R. Ortega, A. Astolfi, G. Bastin, and H. Rodriguez, ``Stabilization of food-chain systems using a port-controlled Hamiltonian description,'' in Proc. Amer. Control Conf., Chicago, IL, USA, 2000, pp. 2245--2249

    2000

  72. [74]

    Diener and R

    E. Diener and R. E. Lucas, ``Personality traits,'' in General Psychology: Required Reading, B. Poteet, Ed. 1em plus 0.5em minus 0.4em Champaign, IL: Diener Education Fund / Noba Project, 2019, pp. 278--295, open educational resource. [Online]. Available: https://nobaproject.com/textbooks/lauren-brewer-new-textbook

    2019

  73. [75]

    Matthews, I

    G. Matthews, I. J. Deary, and M. C. Whiteman, Personality Traits. 1em plus 0.5em minus 0.4em Cambridge, UK: Cambridge University Press, 2003

    2003

  74. [76]

    Z. Liu, W. Xu, W. Zhang, and Q. Jiang, ``An emotion-based personalized music recommendation framework for emotion improvement,'' Inf. Process. Manage., vol. 60, no. 3, May 2023

    2023

  75. [77]

    H. Kaya, F. Gurpinar, and A. Ali Salah, ``Multi-modal score fusion and decision trees for explainable automatic job candidate screening from video cvs,'' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 1--9

    2017

  76. [78]

    Z. Wen, J. Cao, Y. Yang, R. Yang, and S. Liu, ``Affective-nli: Towards accurate and interpretable personality recognition in conversation,'' 2024. [Online]. Available: https://arxiv.org/abs/2404.02589

    work page arXiv 2024

  77. [79]

    invisible hand

    L. Peng, M. Luo, and Y. Guo, ``Deposit ai as the “invisible hand” to make the resale easier: A moderated mediation model,'' Journal of Retailing and Consumer Services, vol. 75, p. 103480, 2023

    2023

  78. [80]

    Y. Ji, W. Wu, H. Zheng, Y. Hu, X. Chen, and L. He, ``Is chatgpt a good personality recognizer? a preliminary study,'' 2023. [Online]. Available: https://arxiv.org/abs/2307.03952

    work page arXiv 2023

  79. [81]

    A. V. Ganesan, Y. K. Lal, A. H. Nilsson, and H. A. Schwartz, ``Systematic evaluation of gpt-3 for zero-shot personality estimation,'' 2023. [Online]. Available: https://arxiv.org/abs/2306.01183

    work page arXiv 2023

  80. [82]

    T. Yang, T. Shi, F. Wan, X. Quan, Q. Wang, B. Wu, and J. Wu, ``Psycot: Psychological questionnaire as powerful chain-of-thought for personality detection,'' 2023. [Online]. Available: https://arxiv.org/abs/2310.20256

    work page arXiv 2023

Showing first 80 references.