Elamur Research⌕
☰
home / papers / 2026 / Says Who? Argument Convincingness and Reader Stance Are Correlated with Perceived Author Personality

Says Who? Argument Convincingness and Reader Stance Are Correlated with Perceived Author Personality

Paper · 2026 · Sabine Weber, Lynn Greschner and Roman Klinger

Summary

The paper asks how readers mentally picture the author of an argument when they have almost no context, and whether that picture is linked to how persuasive they find the argument. The authors reanalyse the ContArgA corpus. In it, crowdworkers judged short arguments framed as statements by a speaker at a town hall meeting, described only by age and gender. Annotators rated convincingness, reported their own stance, education and Big Five traits, and guessed the same properties for the imagined speaker. Statistical analysis shows three things. Readers do form an image of the author. More convincing arguments are attributed to more educated, agreeable and conscientious authors. Readers who agree with an argument's stance imagine its author as more like themselves. In modelling experiments, four generative LLMs failed to match human judgments and gained nothing from a convincingness cue. A RoBERTa regressor trained with that cue predicted perceived personality better. The work links computational argumentation to social meaning, perspectivism and the Halo Effect.

Key points

  • Data: ContArgA contains 800 English arguments. Each has 5 annotations, for 4,000 in total. Annotators were recruited via Prolific and came from the UK and Ireland.
  • Measures: Big Five traits were measured with the Ten-Item Personality Inventory (Gosling et al., 2003). Convincingness was rated on a 1–5 scale.
  • Convincingness and perceived traits: All perceived personality traits correlate with convincingness, and Agreeableness shows the strongest link.
  • Stance and similarity: When annotator and argument stance align, every annotator trait correlates significantly with the matching trait of the imagined author.
  • Modelling: LLMs were tested in three conditions: no convincingness, the annotator's score, or a random value. They did not benefit from the signal, whereas RoBERTa did. Data and code are publicly released through the Emcona project.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of BambergBamberg · Germany5 works · 65 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPhilosophy · 284 worksLiterature and Literary Theory · 519 works

Cite

Cite as Sabine Weber, Lynn Greschner and Roman Klinger. 2026. Says Who? Argument Convincingness and Reader Stance Are Correlated with Perceived Author Personality. The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.wassa-1.20

@inproceedings{weber2026says,
  title = {{Says Who? Argument Convincingness and Reader Stance Are Correlated with Perceived Author Personality}},
  author = {Sabine Weber, Lynn Greschner and Roman Klinger},
  booktitle = {The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.wassa-1.20},
  url = {https://doi.org/10.18653/v1/2026.wassa-1.20}
}

References

30 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Narjis Asad, Nihar Ranjan Sahoo, Rudra Murthy, Swaprava Nath, and Pushpak Bhattacharyya. 2025. “You are beautiful, body image stereotypes are ugly!” BIStereo: A benchmark to measure body image stereotypes in language models. In Findings of the Association for Computational Linguistics: ACL 2025, pag… find
  2. Emily M. Bender, Jonathan T. Morgan, Meghan Oxley, Mark Zachry, Brian Hutchinson, Alex Marin, Bin Zhang, and Mari Ostendorf. 2011. Annotating social acts: Authority claims and alignment moves in Wikipedia talk pages. In Proceedings of the Workshop on Language in Social Media (LSM 2011), pages 48–57,… find
  3. Mary Bucholtz and Kira Hall. 2010. Locating identity in language, pages 18–28. Language and Identities, Edinburgh University Press. find
  4. Silvia Casola, Yang Janet Liu, Siyao Peng, Oliver Kraus, Albert Gatt, and Barbara Plank. 2025. References matter: Investigating the impact of reference set variation on summarization evaluation. In Proceedings of the 18th International Natural Language Generation Conference, pages 274–291, Hanoi, Vi… find
  5. Paul Costa and Robert McCrae. 1999. A five-factor theory of personality. Handbook of personality: Theory and research, 2(01):1999. https://github.com/microsoft/vscode-copilot-chat https://chatgpt.com ↗
  6. Simona Frenda, Gavin Abercrombie, Valerio Basile, Alessandro Pedrani, Raffaella Panizzon, Alessandra Teresa Cignarella, Cristina Marco, and Davide Bernardi. 2024. Perspectivist approaches to natural language processing: a survey. Lang. Resour. Eval., 59(2):1719–1746. find
  7. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, and (many others). 2024. The llama 3 herd of models. arXiv preprint, arXiv:2407.21783.
  8. Lynn Greschner, Sabine Weber, and Roman Klinger. 2025. Trust me, I can convince you: The contextualized argument appraisal framework. arXiv preprint arXiv:2509.17844. Accessed: 2025-10-02. — [arXiv:2509.17844](https://arxiv.org/abs/2509.17844) find
  9. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  10. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock,… find
  11. Kamil Kanclerz, Marcin Gruza, Konrad Karanowski, Julita Bielaniewicz, Piotr Milkowski, Jan Kocon, and Przemyslaw Kazienko. 2022. What if ground truth is subjective? personalized deep neural hate speech detection. In Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022, pages… find
  12. Kyusik Kim, Jeongwoo Ryu, Hyeonseok Jeon, and Bongwon Suh. 2025. Blinded by context: Unveiling the halo effect of MLLM in AI hiring. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26067–26113, Vienna, Austria. Association for Computational Linguistics. find
  13. Anne Kreuter, Kai Sassenberg, and Roman Klinger. 2022. Items from psychometric tests as training data for personality profiling models of Twitter users. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 315–323, Dublin, Ireland.… find
  14. Anne Lauscher, Federico Bianchi, Samuel R. Bowman, and Dirk Hovy. 2022. SocioProbe: What, when, and where language models learn about sociodemographics. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7901–7918, Abu Dhabi, United Arab Emirates. Associ… find
  15. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized bert pretraining approach. CoRR, abs/1907.11692.
  16. Maya Machunsky, Claudia Toma, Vincent Yzerbyt, and Olivier Corneille. 2014. Social projection increases for positive targets: Ascertaining the effect and exploring its antecedents. Personality and Social Psychology Bulletin, 40(10):1373–1388. find
  17. Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Léonard Hussenot, Pier Giuseppe Sessa, Aakanksha Chowdhery, Adam Roberts, Aditya Barua, Alex Botev, Alex Castro-Ros, Ambrose Slone, Amélie… find
  18. Dong Nguyen, A. Seza Doğruöz, Carolyn P. Rosé, and Franciska de Jong. 2016. Computational sociolinguistics: A Survey. Computational Linguistics, 42(3):537–593.
  19. Dong Nguyen, Laura Rosseel, and Jack Grieve. 2021. On learning and representing social meaning in NLP: a sociolinguistic perspective. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 603–612, Onli… find
  20. Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron Courville. 2018. Film: Visual reasoning with a general conditioning layer. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).
  21. Richard E. Petty and John T. Cacioppo. 1986. The elaboration likelihood model of persuasion. volume 19 of Advances in Experimental Social Psychology, pages 123–205. Academic Press. find
  22. Daniele Pizzolli and Carlo Strapparava. 2019. Personality traits recognition in literary texts. In Proceedings of the Second Workshop on Storytelling, pages 107– 111, Florence, Italy. Association for Computational Linguistics. find
  23. E Ashby Plant, Janet Shibley Hyde, Dacher Keltner, and Patricia G Devine. 2000. The gender stereotyping of emotions. Psychology of women quarterly, 24(1):81– 92. find
  24. Carlotta Quensel, Neele Falk, and Gabriella Lapesa. 2025. Investigating subjective factors of argument strength: Storytelling, emotions, and hedging. In Proceedings of the 12th Argument mining Workshop, pages 126–139, Vienna, Austria. Association for Computational Linguistics. find
  25. Yasuaki Sumita, Koh Takeuchi, and Hisashi Kashima. 2025. Cognitive biases in large language models: A survey and mitigation experiments. In Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, SAC ’25, page 1009–1011, New York, NY, USA. Association for Computing Machinery. find
  26. Edward Thorndike. 1920. A constant error in psychological ratings. Journal of applied psychology, 4(1):25– 29. find
  27. Marina Tiuleneva, Vadim A. Porvatov, and Carlo Strapparava. 2024. Big-five backstage: A dramatic dataset for characters personality traits & gender analysis. In Proceedings of the Workshop on Cognitive Aspects of the Lexicon @ LREC-COLING 2024, pages 114–119, Torino, Italia. ELRA and ICCL. find
  28. Ben Verhoeven, Walter Daelemans, and Barbara Plank. 2016. TwiSty: A multilingual Twitter stylometry corpus for gender and personality profiling. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1632–1637, Portorož, Slovenia. European Language… find
  29. Leon Weber-Genzel, Siyao Peng, Marie-Catherine De Marneffe, and Barbara Plank. 2024. VariErr NLI: Separating annotation error from human label variation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2256–2269, Bangkok, Thai…
  30. Diyi Yang, Dirk Hovy, David Jurgens, and Barbara Plank. 2025. Socially aware language technologies: Perspectives and practices. Computational Linguistics, 51:689–703.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/weber-2026-says-who-argument-convincingness-reader/