pith. sign in

arxiv: 2605.17355 · v1 · pith:XSDEKENYnew · submitted 2026-05-17 · 💻 cs.AI · cs.CL

HyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction

Sina Heydari , Majid Ramezani This is my paper

Pith reviewed 2026-05-20 13:26 UTC · model grok-4.3

classification 💻 cs.AI cs.CL
keywords hypergraphpersonality predictiontext analysisBig Five traitsgraph encoderhierarchical modelingnatural language processingautomatic personality assessment
0
0 comments X

The pith

HyperPersona models text as a hypergraph with documents and sentences as hyperedges over words to integrate multi-level cues for more accurate personality prediction from writing alone.

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

The paper sets out to improve automatic personality prediction by treating text as inherently hierarchical rather than flat or sequential. It builds a hypergraph where entire documents and individual sentences serve as connections among words, then runs a transformer-based encoder over that structure to learn how global, local, and lexical features interact. The goal is to extract personality signals that simpler models miss while still using only the text itself. Experiments on standard datasets for the Big Five traits show higher accuracy than existing baselines. This suggests that explicitly preserving textual hierarchy helps the model form more human-like inferences about traits from language.

Core claim

HyperPersona represents a document and its sentences as hyperedges and words as nodes in a hypergraph, then applies a transformer-based graph encoder to learn interactions within and across these linguistic layers, producing context-sensitive representations that yield superior performance on Big Five personality prediction compared with state-of-the-art baselines that rely on shallower or single-level text encodings.

What carries the argument

Multi-level hypergraph in which documents and sentences act as hyperedges linking word nodes, processed by a transformer graph encoder that captures cross-level dependencies.

If this is right

  • The framework integrates global document features, local sentence semantics, and fine-grained word information in a single structured representation.
  • It produces feature representations that are both context-sensitive and grounded in textual hierarchy for personality inference.
  • Performance gains appear on all Big Five dimensions while using only raw text input.
  • The approach demonstrates that ignoring multi-level structure limits how well models can read psychological traits from language.

Where Pith is reading between the lines

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

  • The same hypergraph construction could be tested on other hierarchical text tasks such as multi-level sentiment or topic detection.
  • If the benefit holds, similar structures might improve automated systems that infer user traits for personalization or moderation.
  • Cross-lingual experiments would reveal whether the hierarchy advantage depends on language-specific patterns or holds more generally.

Load-bearing premise

That representing documents and sentences as hyperedges over word nodes and running them through a transformer graph encoder will capture the dependencies relevant to personality traits more effectively than sequential or single-level models.

What would settle it

If a standard transformer or recurrent model achieves equal or higher accuracy on the same Big Five prediction benchmarks without the multi-level hypergraph construction, the claimed advantage of the hypergraph structure would be in question.

Figures

Figures reproduced from arXiv: 2605.17355 by Majid Ramezani, Sina Heydari.

Figure 1
Figure 1. Figure 1: Label distribution for Big Five personality traits in the Essays dataset [PITH_FULL_IMAGE:figures/full_fig_p007_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sentence(a) and Word(b) Distribution in the Essays Dataset [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The overall architecture of HyperPersona [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Multi-level segmentation of a document 9 [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Multi-level vectorization of a segment 10 [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Sample illustration of a hypergraph constructed from a document [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Sample illustration of a hierarchical graph contructed from a hypergraph [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Architecture of the Transformer-Based Graph Encoder [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Architecture of the personality classification with sigmoid-gated latent representation [PITH_FULL_IMAGE:figures/full_fig_p014_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Performance of the HyperPersona across the Big Five personality traits, evaluated using accuracy, f1-score, [PITH_FULL_IMAGE:figures/full_fig_p018_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Comparative prediction accuracy results per personality trait and overall average of HyperPersona against [PITH_FULL_IMAGE:figures/full_fig_p019_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Visulization of ablation study across different representation level combiantion for each Big Five personality [PITH_FULL_IMAGE:figures/full_fig_p019_12.png] view at source ↗
read the original abstract

As a modern commodity, language has become a vast repository of socially and psychologically significant traits and concepts, reflecting the ways people encode pattern of thoughts, behaviors, and emotions into words. Text-based Automatic Personality Prediction (APP), seeks to infer personality from linguistic behavior, offering a scalable alternative to traditional psychometric assessments. Although text is inherently hierarchical, with the document-level capturing global features, the sentence-level encoding local semantics, and the word-level providing fine-grained lexical information, most existing approaches rely on shallow, sequential, or single-level representations that ignore the multi-level structure of written language. To address this, we propose HyperPersona, a framework that explicitly models the hierarchical organization of text (document, sentence, and word) through hypergraph structure, where a document and its sentences are represented as hyperedges, and the words are represented as nodes, enabling joint modeling of global, local, and lexical dependencies of text. Followed by a transformer-based graph encoder that learns interactions within and across these linguistic layers, yielding context-sensitive and structurally grounded feature representations for personality prediction. Experiments on the Big Five personality dimensions show that, while relying solely on text, HyperPersona effectively integrates multi-level linguistic cues, achieving superior performance compared to state-of-the-art baselines. These findings underscore the critical role of textual hierarchy in advancing human-like personality inference from natural language.

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 / 1 minor

Summary. The manuscript proposes HyperPersona, a multi-level hypergraph framework for text-based automatic personality prediction. Documents and sentences are modeled as hyperedges with words as nodes to jointly capture global, local, and lexical linguistic dependencies; a transformer-based graph encoder then learns interactions across these layers for Big Five trait inference. The central claim is that this structure yields superior performance over state-of-the-art baselines while relying solely on text.

Significance. If the empirical superiority holds under rigorous controls, the work would meaningfully advance computational approaches to personality prediction by explicitly encoding textual hierarchy via hypergraphs rather than sequential or flat representations. This could improve both accuracy and interpretability in psychological trait inference from language.

major comments (2)
  1. [Abstract] Abstract: The claim that representing documents/sentences as hyperedges and words as nodes enables better capture of ordered dependencies than sequential models is load-bearing for the central contribution. However, this construction primarily encodes co-occurrence within hyperedges; the manuscript must specify whether and how the transformer-based graph encoder injects explicit positional or sequential signals (e.g., via node features or attention biases) to preserve intra-sentence syntax and order.
  2. [Experiments] Experiments (implied by abstract claims): The assertion of superior performance on Big Five dimensions provides no details on datasets, baseline implementations, evaluation metrics, statistical significance testing, or ablation studies. This omission prevents verification that gains arise from the multi-level hypergraph rather than model capacity or post-hoc selection, directly undermining the main empirical result.
minor comments (1)
  1. [Abstract] Abstract: The description of the framework is dense; a short schematic or explicit statement of how hyperedges are constructed from raw text would improve immediate clarity.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed comments on our manuscript. These observations help clarify how we can better articulate the model's handling of textual structure and strengthen the empirical presentation. We address each major comment below and indicate the corresponding revisions.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that representing documents/sentences as hyperedges and words as nodes enables better capture of ordered dependencies than sequential models is load-bearing for the central contribution. However, this construction primarily encodes co-occurrence within hyperedges; the manuscript must specify whether and how the transformer-based graph encoder injects explicit positional or sequential signals (e.g., via node features or attention biases) to preserve intra-sentence syntax and order.

    Authors: We agree that the current description does not sufficiently specify how ordered dependencies are preserved beyond co-occurrence. The hypergraph primarily models multi-way relations, and while the transformer graph encoder operates on the resulting structure, explicit mechanisms for sequential signals were not detailed. We will revise the Methods section to describe the addition of positional encodings to word node features (derived from sentence order) and relative position biases within the attention layers of the graph transformer. This will clarify how intra-sentence syntax is respected and directly address the load-bearing claim. revision: yes

  2. Referee: [Experiments] Experiments (implied by abstract claims): The assertion of superior performance on Big Five dimensions provides no details on datasets, baseline implementations, evaluation metrics, statistical significance testing, or ablation studies. This omission prevents verification that gains arise from the multi-level hypergraph rather than model capacity or post-hoc selection, directly undermining the main empirical result.

    Authors: The referee is correct that the experimental details provided are insufficient for full verification and reproducibility. While the manuscript references standard Big Five datasets and reports comparative results, it lacks explicit descriptions of baseline re-implementations, exact evaluation metrics per trait, statistical tests, and ablations isolating each hypergraph level. We will expand the Experiments section with these elements, including tables for ablation results and significance testing, to demonstrate that performance gains stem from the proposed multi-level structure. revision: yes

Circularity Check

0 steps flagged

No significant circularity; framework is an independent modeling choice

full rationale

The paper presents HyperPersona as a proposed architectural framework that represents documents and sentences as hyperedges with words as nodes, then applies a transformer-based graph encoder to integrate multi-level linguistic cues for personality prediction. This is an explicit modeling decision grounded in the hierarchical nature of text, not a derivation that reduces to fitted parameters or prior self-citations by construction. No equations are shown that equate outputs to inputs tautologically, and performance claims rest on empirical experiments against baselines rather than self-referential logic. The central claim remains independently falsifiable via external benchmarks and does not rely on load-bearing self-citations or ansatzes smuggled from prior work.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The framework rests on standard assumptions from graph neural networks and transformers plus the domain assumption that personality traits are reliably encoded in multi-level linguistic structure; no free parameters or invented physical entities are described.

axioms (2)
  • domain assumption Text is inherently hierarchical with document-level global features, sentence-level local semantics, and word-level lexical information.
    Invoked in the opening paragraph to justify the multi-level hypergraph design.
  • ad hoc to paper Hyperedges connecting a document and its sentences to words enable joint modeling of global, local, and lexical dependencies.
    Core modeling choice presented as the solution to limitations of shallow or sequential representations.

pith-pipeline@v0.9.0 · 5770 in / 1343 out tokens · 48545 ms · 2026-05-20T13:26:07.663459+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

72 extracted references · 72 canonical work pages

  1. [1]

    The principles of psychology.Henry Holt, 1890

    William James. The principles of psychology.Henry Holt, 1890

    work page

  2. [2]

    A five-factor theory of personality.Handbook of personality: Theory and research, 2(1999):139–153, 1999

    Robert R McCrae and Paul T Costa Jr. A five-factor theory of personality.Handbook of personality: Theory and research, 2(1999):139–153, 1999

    work page 1999

  3. [3]

    John wiley & sons, 2011

    Manuel Castells.The rise of the network society. John wiley & sons, 2011

    work page 2011

  4. [4]

    Predicting personality with social media

    Jennifer Golbeck, Cristina Robles, and Karen Turner. Predicting personality with social media. InCHI ’11 Extended Abstracts on Human Factors in Computing Systems, CHI EA ’11, page 253–262, New York, NY , USA,

    work page

  5. [5]

    Association for Computing Machinery

    work page

  6. [6]

    Text-based automatic personality prediction: a bibliographic review.J

    Ali-Reza Feizi-Derakhshi, Mohammad-Reza Feizi-Derakhshi, Majid Ramezani, Narjes Nikzad-Khasmakhi, Meysam Asgari-Chenaghlu, Taymaz Akan, Mehrdad Ranjbar-Khadivi, Elnaz Zafarni-Moattar, and Zoleikha Jahanbakhsh-Naghadeh. Text-based automatic personality prediction: a bibliographic review.J. Comput. Soc. Sci., 5(2):1555–1593, nov 2022

    work page 2022

  7. [7]

    Big five inventory.Journal of personality and social psychology, 1991

    Oliver P John, Eileen M Donahue, and Robert L Kentle. Big five inventory.Journal of personality and social psychology, 1991

    work page 1991

  8. [8]

    The revised neo personality inventory (neo-pi-r).The SAGE handbook of personality theory and assessment, 2(2):179–198, 2008

    Paul T Costa and Robert R McCrae. The revised neo personality inventory (neo-pi-r).The SAGE handbook of personality theory and assessment, 2(2):179–198, 2008

    work page 2008

  9. [9]

    P. T. Costa and R. R. McCrae. Normal personality assessment in clinical practice: the neo personality inventory. Psychological Assessment, 4:5–13, 1992

    work page 1992

  10. [10]

    Personality structure: Emergence of the five-factor model.Annu

    J M Digman. Personality structure: Emergence of the five-factor model.Annu. Rev. Psychol., 41(1):417–440, jan 1990

    work page 1990

  11. [11]

    Assessing the universal structure of personality in early adolescence: The NEO-PI-R and NEO-PI-3 in 24 cultures.Assessment, 16(3):301–311, may 2009

    Filip De Fruyt, Marleen De Bolle, Robert R McCrae, Antonio Terracciano, Paul T Costa, Jr, and Collaborators of the Adolescent Personality Profiles of Cultures Project. Assessing the universal structure of personality in early adolescence: The NEO-PI-R and NEO-PI-3 in 24 cultures.Assessment, 16(3):301–311, may 2009

    work page 2009

  12. [12]

    Self-report questionnaires to measure big five personality traits in children and adolescents: A systematic review.Scand

    Giada Vicentini, Daniela Raccanello, and Roberto Burro. Self-report questionnaires to measure big five personality traits in children and adolescents: A systematic review.Scand. J. Psychol., apr 2025

    work page 2025

  13. [13]

    Linguistic inquiry and word count: Liwc 2001

    James W Pennebaker, Martha E Francis, Roger J Booth, et al. Linguistic inquiry and word count: Liwc 2001. Mahway: Lawrence Erlbaum Associates, 71(2001):2001, 2001

    work page 2001

  14. [14]

    Lexical predictors of personality type

    Shlomo Argamon, Sushant Dhawle, Moshe Koppel, and James W Pennebaker. Lexical predictors of personality type. InProceedings of the 2005 joint annual meeting of the interface and the classification society of North America, pages 1–16. USA), 2005

    work page 2005

  15. [15]

    Andrew Schwartz, Johannes C

    H. Andrew Schwartz, Johannes C. Eichstaedt, Margaret L. Kern, Lukasz Dziurzynski, Stephanie M. Ramones, Megha Agrawal, Achal Shah, Michal Kosinski, David Stillwell, Martin E. P. Seligman, and Lyle H. Ungar. Personality, gender, and age in the language of social media: The open-vocabulary approach.PLOS ONE, 8(9):1–16, 09 2013

    work page 2013

  16. [16]

    Predicting personality from patterns of behavior collected with smartphones.Proc Natl Acad Sci U S A, 117(30):17680–17687, jul 2020

    Clemens Stachl, Quay Au, Ramona Schoedel, Samuel D Gosling, Gabriella M Harari, Daniel Buschek, Sarah Theres Völkel, Tobias Schuwerk, Michelle Oldemeier, Theresa Ullmann, Heinrich Hussmann, Bernd Bischl, and Markus Bühner. Predicting personality from patterns of behavior collected with smartphones.Proc Natl Acad Sci U S A, 117(30):17680–17687, jul 2020

    work page 2020

  17. [17]

    Deep learning-based document modeling for personality detection from text.IEEE Intelligent Systems, 32(2):74–79, 2017

    Navonil Majumder, Soujanya Poria, Alexander Gelbukh, and Erik Cambria. Deep learning-based document modeling for personality detection from text.IEEE Intelligent Systems, 32(2):74–79, 2017

    work page 2017

  18. [18]

    Andrew Schwartz

    Veronica Lynn, Niranjan Balasubramanian, and H. Andrew Schwartz. Hierarchical modeling for user personality prediction: The role of message-level attention. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors,Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5306– 5316, Online, jul 2020. ...

    work page 2020

  19. [19]

    Personality recognition using convolutional neural networks

    Maite Giménez, Roberto Paredes, and Paolo Rosso. Personality recognition using convolutional neural networks. In Alexander Gelbukh, editor,Computational Linguistics and Intelligent Text Processing, pages 313–323, Cham,

    work page

  20. [20]

    21 APREPRINT- MAY19, 2026

    Springer International Publishing. 21 APREPRINT- MAY19, 2026

    work page 2026

  21. [21]

    Bert: Pre-training of deep bidirectional transformers for language understanding, 2019

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding, 2019

    work page 2019

  22. [22]

    Roberta: A robustly optimized bert pretraining approach, 2019

    Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach, 2019

    work page 2019

  23. [23]

    Xlnet: Generalized autoregressive pretraining for language understanding

    Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. Xlnet: Generalized autoregressive pretraining for language understanding. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors,Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019

    work page 2019

  24. [24]

    Attention is all you need

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. Attention is all you need. In I. Guyon, U. V on Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors,Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017

    work page 2017

  25. [25]

    Recent trends in deep learning based personality detection.Artificial Intelligence Review, 53(4):2313–2339, apr 2020

    Yash Mehta, Navonil Majumder, Alexander Gelbukh, and Erik Cambria. Recent trends in deep learning based personality detection.Artificial Intelligence Review, 53(4):2313–2339, apr 2020

    work page 2020

  26. [26]

    Hans Christian, Derwin Suhartono, Andry Chowanda, and Kamal Z. Zamli. Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging.Journal of Big Data, 8(1):68, 2021

    work page 2021

  27. [27]

    Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu. A comprehensive survey on graph neural networks.IEEE Transactions on Neural Networks and Learning Systems, 32(1):4–24, 2021

    work page 2021

  28. [28]

    Graph neural networks for text classification: a survey

    Kunze Wang, Yihao Ding, and Soyeon Caren Han. Graph neural networks for text classification: a survey. Artificial Intelligence Review, 57(8):190, Jul 2024

    work page 2024

  29. [29]

    Psycholinguistic tripartite graph network for personality detection

    Tao Yang, Feifan Yang, Haolan Ouyang, and Xiaojun Quan. Psycholinguistic tripartite graph network for personality detection. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors,Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (...

    work page 2021

  30. [30]

    Automatic personality prediction: an enhanced method using ensemble modeling.Neural Computing and Applications, 34(21):18369–18389, nov 2022

    Majid Ramezani, Mohammad-Reza Feizi-Derakhshi, Mohammad-Ali Balafar, Meysam Asgari-Chenaghlu, Ali- Reza Feizi-Derakhshi, Narjes Nikzad-Khasmakhi, Mehrdad Ranjbar-Khadivi, Zoleikha Jahanbakhsh-Nagadeh, Elnaz Zafarani-Moattar, and Taymaz Akan. Automatic personality prediction: an enhanced method using ensemble modeling.Neural Computing and Applications, 34(...

    work page 2022

  31. [31]

    Data augmented graph neural networks for personality detection.Proceedings of the AAAI Conference on Artificial Intelligence, 38(1):664–672, Mar

    Yangfu Zhu, Yue Xia, Meiling Li, Tingting Zhang, and Bin Wu. Data augmented graph neural networks for personality detection.Proceedings of the AAAI Conference on Artificial Intelligence, 38(1):664–672, Mar. 2024

    work page 2024

  32. [32]

    Distributed representations of words and phrases and their compositionality

    Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed representations of words and phrases and their compositionality. In C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, editors,Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc., 2013

    work page 2013

  33. [33]

    Skip-thought vectors

    Ryan Kiros, Yukun Zhu, Russ R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. Skip-thought vectors. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors,Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015

    work page 2015

  34. [34]

    Distributed representations of sentences and documents

    Quoc Le and Tomas Mikolov. Distributed representations of sentences and documents. In Eric P. Xing and Tony Jebara, editors,Proceedings of the 31st International Conference on Machine Learning, volume 32, 2 of Proceedings of Machine Learning Research, pages 1188–1196, Bejing, China, 22–24 Jun 2014. PMLR

    work page 2014

  35. [35]

    Graph transformer for graph-to-sequence learning.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7464–7471, Apr

    Deng Cai and Wai Lam. Graph transformer for graph-to-sequence learning.Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7464–7471, Apr. 2020

    work page 2020

  36. [36]

    Veronica Ong, Anneke D. S. Rahmanto, Williem, Derwin Suhartono, Aryo E. Nugroho, Esther W. Andangsari, and Muhamad N. Suprayogi. Personality prediction based on twitter information in bahasa indonesia. In2017 Federated Conference on Computer Science and Information Systems (FedCSIS), pages 367–372, 2017

    work page 2017

  37. [37]

    Understanding email writers: Personality prediction from email messages

    Jianqiang Shen, Oliver Brdiczka, and Juan Liu. Understanding email writers: Personality prediction from email messages. In Sandra Carberry, Stephan Weibelzahl, Alessandro Micarelli, and Giovanni Semeraro, editors,User Modeling, Adaptation, and Personalization, pages 318–330, Berlin, Heidelberg, 2013. Springer Berlin Heidelberg

    work page 2013

  38. [38]

    Fusing social media cues: Personality prediction from twitter and instagram

    Marcin Skowron, Marko Tkalˇciˇc, Bruce Ferwerda, and Markus Schedl. Fusing social media cues: Personality prediction from twitter and instagram. InProceedings of the 25th International Conference Companion on World Wide Web, WWW ’16 Companion, page 107–108, Republic and Canton of Geneva, CHE, 2016. International World Wide Web Conferences Steering Committ...

    work page 2016

  39. [39]

    Chapter four - text-based personality prediction using xlnet

    Ashok Kumar Jayaraman, Gayathri Ananthakrishnan, Tina Esther Trueman, and Erik Cambria. Chapter four - text-based personality prediction using xlnet. In Preetha Evangeline David and P. Anandhakumar, editors,Applying Computational Intelligence for Social Good, volume 132 ofAdvances in Computers, pages 49–65. Elsevier, 2024

    work page 2024

  40. [40]

    Big five personality prediction based on pre-training language model and sentiment knowledge base

    Hao Lin and Xiaolei Li. Big five personality prediction based on pre-training language model and sentiment knowledge base. In Huajun Dong and Shijie Jia, editors,Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), volume 12800, page 128004I. International Society for Optics and Photonics, SPIE, 2023

    work page 2023

  41. [41]

    Personality prediction model for social media using machine learning technique.Computers and Electrical Engineering, 100:107852, 2022

    Murari Devakannan Kamalesh and Bharathi B. Personality prediction model for social media using machine learning technique.Computers and Electrical Engineering, 100:107852, 2022

    work page 2022

  42. [42]

    Andrew Schwartz

    Adithya V Ganesan, Yash Kumar Lal, August Nilsson, and H. Andrew Schwartz. Systematic evaluation of GPT-3 for zero-shot personality estimation. In Jeremy Barnes, Orphée De Clercq, and Roman Klinger, editors, Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 390–400, Toronto, Canada, jul...

    work page 2023

  43. [43]

    Using transformers and bi-lstm with sentence embeddings for prediction of openness human personality trait.PeerJ Computer Science, 11:e2781, 2025

    Anam Naz, Hikmat Ullah Khan, Tariq Alsahfi, Mousa Alhajlah, Bader Alshemaimri, and Ali Daud. Using transformers and bi-lstm with sentence embeddings for prediction of openness human personality trait.PeerJ Computer Science, 11:e2781, 2025

    work page 2025

  44. [44]

    Multilingual transformer-based personal- ity traits estimation.Information, 11(4), 2020

    Simone Leonardi, Diego Monti, Giuseppe Rizzo, and Maurizio Morisio. Multilingual transformer-based personal- ity traits estimation.Information, 11(4), 2020

    work page 2020

  45. [45]

    Personality trait detection using bagged svm over bert word embedding ensembles, 2020

    Amirmohammad Kazameini, Samin Fatehi, Yash Mehta, Sauleh Eetemadi, and Erik Cambria. Personality trait detection using bagged svm over bert word embedding ensembles, 2020

    work page 2020

  46. [46]

    Using deep learning and word embeddings for predicting human agreeableness behavior.Sci Rep, 14(1):29875, dec 2024

    Raed Alsini, Anam Naz, Hikmat Ullah Khan, Amal Bukhari, Ali Daud, and Muhammad Ramzan. Using deep learning and word embeddings for predicting human agreeableness behavior.Sci Rep, 14(1):29875, dec 2024

    work page 2024

  47. [47]

    Text-based automatic personal- ity prediction using kgrat-net: a knowledge graph attention network classifier.Scientific reports, 12(1):21453, 2022

    Majid Ramezani, Mohammad-Reza Feizi-Derakhshi, and Mohammad-Ali Balafar. Text-based automatic personal- ity prediction using kgrat-net: a knowledge graph attention network classifier.Scientific reports, 12(1):21453, 2022

    work page 2022

  48. [48]

    A lexical psycholinguistic knowledge-guided graph neural network for interpretable personality detection.Knowledge-Based Systems, 249:108952, 2022

    Yangfu Zhu, Linmei Hu, Nianwen Ning, Wei Zhang, and Bin Wu. A lexical psycholinguistic knowledge-guided graph neural network for interpretable personality detection.Knowledge-Based Systems, 249:108952, 2022

    work page 2022

  49. [49]

    An aspect-aware enhanced psycholinguistic knowledge graph-based personality detection using deep learning.SN Computer Science, 4(3):293, mar 2023

    Sirasapalli Joshua Johnson and M Ramakrishna Murty. An aspect-aware enhanced psycholinguistic knowledge graph-based personality detection using deep learning.SN Computer Science, 4(3):293, mar 2023

    work page 2023

  50. [50]

    Pushing on personality detection from verbal behavior: A transformer meets text contours of psycholinguistic features

    Elma Kerz, Yu Qiao, Sourabh Zanwar, and Daniel Wiechmann. Pushing on personality detection from verbal behavior: A transformer meets text contours of psycholinguistic features. In Jeremy Barnes, Orphée De Clercq, Valentin Barriere, Shabnam Tafreshi, Sawsan Alqahtani, João Sedoc, Roman Klinger, and Alexandra Balahur, editors,Proceedings of the 12th Worksho...

    work page 2022

  51. [51]

    Ghazal Mohammed Salahat, Liaqat Ali and Haitham M

    Taher M. Ghazal Mohammed Salahat, Liaqat Ali and Haitham M. Alzoubi. Personality assessment based on natural stream of thoughts empowered with machine learning.Computers, Materials and Continua, 76(1):1–17, 2023

    work page 2023

  52. [52]

    A hierarchical transformer network with label attention for personality prediction by mbti classification.Applied Soft Computing, 178:113267, 2025

    S Bama, MS Hema, S Esakkirajan, and M Nageswara Guptha. A hierarchical transformer network with label attention for personality prediction by mbti classification.Applied Soft Computing, 178:113267, 2025

    work page 2025

  53. [53]

    Kai Yang, Raymond Y . K. Lau, and Ahmed Abbasi. Getting personal: A deep learning artifact for text-based measurement of personality.Information Systems Research, 34(1):194–222, 2023

    work page 2023

  54. [54]

    Multi-document transformer for personality detection

    Feifan Yang, Xiaojun Quan, Yunyi Yang, and Jianxing Yu. Multi-document transformer for personality detection. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16):14221–14229, May 2021

    work page 2021

  55. [55]

    A language-independent and compositional model for personality trait recognition from short texts, 2016

    Fei Liu, Julien Perez, and Scott Nowson. A language-independent and compositional model for personality trait recognition from short texts, 2016

    work page 2016

  56. [56]

    Multilevel sentence embeddings for personality prediction, 2023

    Paolo Tirotta, Akira Yuasa, and Masashi Morita. Multilevel sentence embeddings for personality prediction, 2023

    work page 2023

  57. [57]

    A survey on hypergraph representation learning.ACM Comput

    Alessia Antelmi, Gennaro Cordasco, Mirko Polato, Vittorio Scarano, Carmine Spagnuolo, and Dingqi Yang. A survey on hypergraph representation learning.ACM Comput. Surv., 56(1), August 2023

    work page 2023

  58. [58]

    Bruce Croft

    Michael Bendersky and W. Bruce Croft. Modeling higher-order term dependencies in information retrieval using query hypergraphs. InProceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’12, page 941–950, New York, NY , USA, 2012. Association for Computing Machinery. 23 APREPRINT- MAY19, 2026

    work page 2012

  59. [59]

    Linguistic styles: language use as an individual difference.Journal of personality and social psychology, 77(6):1296, 1999

    James W Pennebaker and Laura A King. Linguistic styles: language use as an individual difference.Journal of personality and social psychology, 77(6):1296, 1999

    work page 1999

  60. [60]

    How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings.arXiv preprint arXiv:1909.00512, 2019

    Kawin Ethayarajh. How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings.arXiv preprint arXiv:1909.00512, 2019

    work page arXiv 1909

  61. [61]

    Universal text representation from bert: An empirical study, 2019

    Xiaofei Ma, Zhiguo Wang, Patrick Ng, Ramesh Nallapati, and Bing Xiang. Universal text representation from bert: An empirical study, 2019

    work page 2019

  62. [62]

    Active Learning for BERT: An Empirical Study

    Liat Ein-Dor, Alon Halfon, Ariel Gera, Eyal Shnarch, Lena Dankin, Leshem Choshen, Marina Danilevsky, Ranit Aharonov, Yoav Katz, and Noam Slonim. Active Learning for BERT: An Empirical Study. In Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu, editors,Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7...

    work page 2020

  63. [63]

    Knowledge graph-enabled text-based automatic personality prediction.Computational Intelligence and Neuroscience, 2022(1):3732351, 2022

    Majid Ramezani, Mohammad-Reza Feizi-Derakhshi, and Mohammad-Ali Balafar. Knowledge graph-enabled text-based automatic personality prediction.Computational Intelligence and Neuroscience, 2022(1):3732351, 2022

    work page 2022

  64. [64]

    Encoding text information with graph convolutional networks for personality recognition.Applied Sciences, 10(12), 2020

    Zhe Wang, Chun-Hua Wu, Qing-Biao Li, Bo Yan, and Kang-Feng Zheng. Encoding text information with graph convolutional networks for personality recognition.Applied Sciences, 10(12), 2020

    work page 2020

  65. [65]

    Deep learning based fusion strategies for personality prediction.Egyptian Informatics Journal, 23(1):47–53, 2022

    Kamal El-Demerdash, Reda A El-Khoribi, Mahmoud A Ismail Shoman, and Sherif Abdou. Deep learning based fusion strategies for personality prediction.Egyptian Informatics Journal, 23(1):47–53, 2022

    work page 2022

  66. [66]

    spacy: Industrial-strength natural language processing in python

    Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. spacy: Industrial-strength natural language processing in python. 2020

    work page 2020

  67. [67]

    Exploring network structure, dynamics, and function using networkx

    Aric Hagberg, Pieter J Swart, and Daniel A Schult. Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Laboratory (LANL), Los Alamos, NM (United States), 2008

    work page 2008

  68. [68]

    Hypernetx: A python package for modeling complex network data as hypergraphs, 2023

    Brenda Praggastis, Sinan Aksoy, Dustin Arendt, Mark Bonicillo, Cliff Joslyn, Emilie Purvine, Madelyn Shapiro, and Ji Young Yun. Hypernetx: A python package for modeling complex network data as hypergraphs, 2023

    work page 2023

  69. [69]

    Pytorch: An imperative style, high-performance deep learning library, 2019

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. Pytorch: An imperative style, high-performa...

    work page 2019

  70. [70]

    Fast graph representation learning with pytorch geometric, 2019

    Matthias Fey and Jan Eric Lenssen. Fast graph representation learning with pytorch geometric, 2019

    work page 2019

  71. [71]

    Personality trait classification of essays with the application of feature reduction

    Edward Tighe, Jennifer Ureta, Bernard Pollo, Charibeth Cheng, and Remedios Bulos. Personality trait classification of essays with the application of feature reduction. 07 2016

    work page 2016

  72. [72]

    Automatic text-based personality recognition on monologues and multiparty dialogues using attentive networks and contextual embeddings (student abstract)

    Hang Jiang, Xianzhe Zhang, and Jinho D Choi. Automatic text-based personality recognition on monologues and multiparty dialogues using attentive networks and contextual embeddings (student abstract). InProceedings of the AAAI conference on artificial intelligence, volume 34, 10, pages 13821–13822, 2020. 24

    work page 2020