CoChat
Sign Up
Cited by 4Authorship Attribution and ProfilingDigital Media Forensic DetectionTopic Modeling

The DOI matches its Crossref record; the references it cites are not checked yet.

Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition

Open access
Cowap, Alan, Graham, Yvette, Foster, Jennifer·2023·Findings of the Association for Computational Linguistics: EMNLP 2023
DOI 10.18653/v1/2023.findings-emnlp.665
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent developments in generative AI have shone a spotlight on high-performance synthetic text generation technologies.The now wide availability and ease of use of such models highlights the urgent need to provide equally powerful technologies capable of identifying synthetic text.With this in mind, we draw inspiration from psychological studies which suggest that people can be driven by emotion and encode emotion in the text they compose.We hypothesize that pretrained language models (PLMs) have an affective deficit because they lack such an emotional driver when generating text and consequently may generate synthetic text which has affective incoherence i.e. lacking the kind of emotional coherence present in human-authored text.We subsequently develop an emotionally aware detector by fine-tuning a PLM on emotion.Experiment results indicate that our emotionallyaware detector achieves improvements across a range of synthetic text generators, various sized models, datasets, and domains.Finally, we compare our emotionally-aware synthetic text detector to ChatGPT in the task of identification of its own output and show substantial gains, reinforcing the potential of emotion as a signal to identify synthetic text.Code, models, and datasets are available at https: //github.com/alanagiasi/emoPLMsynth

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2023.findings-emnlp.665

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists haven’t been fetched yet

References 51 · Cited by 4

Research works printed but not linked: 43

  1. David Ifeoluwa Adelani, Haotian Mai, Fuming Fang, Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen. 2019. Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Mod- els and Their Human-and Machine-based Detection. arXiv:1907.09177 [cs]. ArXiv: 1907.09177. · arXiv
  2. Ameeta Agrawal, Aijun An, and Manos Papagelis. 2018. Learning Emotion-enriched Word Representations. In Proceedings of the 27th International Conference on Computational Linguistics, pages 950-961, Santa Fe, New Mexico, USA. Association for Computa- tional Linguistics.
  3. Kushal Arora, Layla El Asri, Hareesh Bahuleyan, and Jackie Chi Kit Cheung. 2022. Why Expo- sure Bias Matters: An Imitation Learning Perspec- tive of Error Accumulation in Language Generation. ArXiv:2204.01171 [cs. · DOI
  4. Meghana Moorthy Bhat and Srinivasan Parthasarathy. 2020. How Effectively Can Machines Defend Against Machine-Generated Fake News? An Empiri- cal Study. In Proceedings of the First Workshop on Insights from Negative Results in NLP, pages 48-53, Online. Association for Computational Linguistics.
  5. Catherine M. Bohn-Gettler and David N. Rapp. 2014. Emotion during reading and writing. In Interna- tional handbook of emotions in education, Educa- tional psychology handbook series, pages 437-457. Routledge/Taylor & Francis Group, New York, NY, US.
  6. Laura Ana Maria Bostan, Evgeny Kim, and Roman Klinger. 2020. GoodNewsEveryone: A Corpus of News Headlines Annotated with Emotions, Seman- tic Roles, and Reader Perception. In Proceedings of the 12th Language Resources and Evaluation Confer- ence, pages 1554-1566, Marseille, France. European Language Resources Association.
  7. Laura-Ana-Maria Bostan and Roman Klinger. 2018. An Analysis of Annotated Corpora for Emotion Classi- fication in Text. In Proceedings of the 27th Inter- national Conference on Computational Linguistics, pages 2104-2119, Santa Fe, New Mexico, USA. As- sociation for Computational Linguistics.
  8. Alice Brand. 1991. Social Cognition, Emotions, and the Psychology of Writing. Journal of Advanced Composition, 11(2):395-407. Publisher: JAC.
  9. Alice G. Brand. 1985. HOT COGNITION: EMO- TIONS AND WRITING BEHAVIOR. Journal of Advanced Composition, 6:5-15. Publisher: JAC.
  10. Alice G. Brand. 1987. The Why of Cognition: Emotion and the Writing Process. College Composition and Communication, 38(4):436-443. Publisher: National Council of Teachers of English. · DOI
  11. Paul Ekman. 1992. An argument for basic emotions. Cognition and Emotion, 6(3/4):169-200. · DOI · Paper page
  12. Paul Ekman. 1999. Basic Emotions. In Handbook of Cognition and Emotion, pages 45-60. · DOI · Paper page
  13. Paul Ekman. 2016. What Scientists Who Study Emo- tion Agree About. Perspectives on Psychological Science, 11(1):31-34. · DOI
  14. Catherine A. Gao, Frederick M. Howard, Nikolay S. Markov, Emma C. Dyer, Siddhi Ramesh, Yuan Luo, and Alexander T. Pearson. 2022. Comparing scien- tific abstracts generated by ChatGPT to original ab- stracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers. Pages: 2022.12.23.521610 Section: New Results. · DOI · Paper page
  15. Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A. Smith. 2020. RealToxi- cityPrompts: Evaluating Neural Toxic Degeneration in Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3356-3369, Online. Association for Computational Linguistics. · DOI · Paper page
  16. Saurabh Gupta, Hong Huy Nguyen, Junichi Yamag- ishi, and Isao Echizen. 2020. Viable Threat on News Reading: Generating Biased News Using Natural Language Models. In Proceedings of the Fourth Workshop on Natural Language Processing and Com- putational Social Science, pages 55-65, Online. As- sociation for Computational Linguistics. · DOI
  17. Chenyang Huang, Osmar Zaïane, Amine Trabelsi, and Nouha Dziri. 2018. Automatic Dialogue Genera- tion with Expressed Emotions. In Proceedings of the 2018 Conference of the North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Pa- pers), pages 49-54, New Orleans, Louisiana. Associ- ation for Computational Linguistics. · DOI
  18. Susanne Knaller. 2017. Emotions and the Process of Writing. In Ingeborg Jandl, Susanne Knaller, Sabine Schönfellner, and Gudrun Tockner, editors, Lettre, 1 edition, pages 17-28. transcript Verlag, Bielefeld, Germany. · DOI
  19. Bernhard Kratzwald, Suzana Ilic, Mathias Kraus, Stefan Feuerriegel, and Helmut Prendinger. 2018. Deep learning for affective computing: text-based emotion recognition in decision support. Decision Support Systems, 115:24-35. ArXiv: 1803.06397. · DOI
  20. Michela Lorandi and Anya Belz. 2023. How to Con- trol Sentiment in Text Generation: A Survey of the State-of-the-Art in Sentiment-Control Techniques. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Me- dia Analysis, Toronto, Canada.
  21. Amil Merchant, Elahe Rahimtoroghi, Ellie Pavlick, and Ian Tenney. 2020. What Happens To BERT Embed- dings During Fine-tuning? In Proceedings of the Third BlackboxNLP Workshop on Analyzing and In- terpreting Neural Networks for NLP, pages 33-44, Online. Association for Computational Linguistics. · DOI
  22. Tomás Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Represen- tations in Vector Space. In 1st International Con- ference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings.
  23. Sinno Jialin Pan and Qiang Yang. 2010. A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10):1345-1359. Confer- ence Name: IEEE Transactions on Knowledge and Data Engineering. · DOI · Paper page
  24. Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, and Zaid Harchaoui. 2021. MAUVE: Measuring the Gap Be- tween Neural Text and Human Text using Divergence Frontiers. In Advances in Neural Information Pro- cessing Systems.
  25. ROBERT Plutchik. 1980. Chapter 1 -A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMO- TION. In Robert Plutchik and Henry Kellerman, editors, Theories of Emotion, pages 3-33. Academic Press. · DOI · Paper page
  26. Robert Plutchik. 2001. The Nature of Emotions: Hu- man emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. American Scientist, 89(4):344- 350. Publisher: Sigma Xi, The Scientific Research Society.
  27. Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2016. Sequence Level Train- ing with Recurrent Neural Networks. In ICLR 2016.
  28. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y.-Lan Boureau. 2019. Towards Empathetic Open-domain Conversation Models: a New Bench- mark and Dataset. arXiv:1811.00207 [cs]. ArXiv: 1811.00207. · arXiv
  29. Enrico Santus, Qin Lu, Alessandro Lenci, and Chu-Ren Huang. 2014. Taking Antonymy Mask off in Vec- tor Space. In Proceedings of the 28th Pacific Asia Garda, Shlok S. Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Simon Ott, Sinee Sang-aroonsiri, Sr- ishti Kumar, Stefan Schweter, Sushil Bharati, Tan- may Laud, Théo Gigant, Tomoya Kainuma, Wo- jciech Kusa, Yanis Labrak, Yash Shailesh Bajaj, Yash Venkatraman, Yifan Xu, Yingxin Xu, Yu Xu, Zhe Tan, Zhongli Xie, Zifan Ye, Mathilde Bras, Younes Belkada, and Thomas Wolf. 2023. BLOOM: A 176B-Parameter Open-Access Multilingual Lan- guage Model. ArXiv:2211.05100 [cs]. · DOI · Paper page
  30. Armin Seyeditabari, Narges Tabari, Shafie Gholizade, and Wlodek Zadrozny. 2019. Emotional Embed- dings: Refining Word Embeddings to Capture Emo- tional Content of Words. arXiv:1906.00112 [cs]. ArXiv: 1906.00112. · arXiv
  31. Armin Seyeditabari and Wlodek Zadrozny. 2017. Can Word Embeddings Help Find Latent Emotions in Text? Preliminary Results. In The Thirtieth Interna- tional Flairs Conference.
  32. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Tree- bank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631-1642, Seattle, Washington, USA. Asso- ciation for Computational Linguistics.
  33. Charles D. Spielberger. 1972. Anxiety as an Emotional State. In Charles D. Spielberger, editor, Anxiety: Current trends and research, volume 1. New York Academic Press. Book Title: Anxiety. · DOI · Paper page
  34. C. Strapparava and Rada Mihalcea. 2008. Learning to identify emotions in text. In SAC '08. · DOI
  35. Carlo Strapparava and Rada Mihalcea. 2007. SemEval- 2007 Task 14: Affective Text. In Proceedings of the Fourth International Workshop on Semantic Evalua- tions (SemEval-2007), pages 70-74, Prague, Czech Republic. Association for Computational Linguistics.
  36. Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, and Dongwon Lee. 2021. TURINGBENCH: A Bench- mark Environment for Turing Test in the Age of Neu- ral Text Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2001-2016, Punta Cana, Dominican Republic. Asso- ciation for Computational Linguistics.
  37. Alex Wang, Yada Pruksachatkun, Nikita Nangia, Aman- preet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2019. SuperGLUE: A Stickier Benchmark for General-Purpose Language Under- standing Systems. In Advances in Neural Informa- tion Processing Systems, volume 32.
  38. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: An- alyzing and Interpreting Neural Networks for NLP, pages 353-355, Brussels, Belgium. Association for Computational Linguistics. · DOI · Paper page
  39. Shuo Wang, Aishan Maoliniyazi, Xinle Wu, and Xi- aofeng Meng. 2020a. Emo2Vec: Learning Emotional Embeddings via Multi-Emotion Category. ACM Transactions on Internet Technology, 20(2):13:1- 13:17. · DOI
  40. Yan Wang, Jiayu Zhang, Jun Ma, Shaojun Wang, and Jing Xiao. 2020b. Contextualized Emotion Recogni- tion in Conversation as Sequence Tagging. In Pro- ceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 186-195, 1st virtual meeting. Association for Com- putational Linguistics.
  41. Linyi Yang, Yaoxiao Song, Xuan Ren, Chenyang Lyu, Yidong Wang, Lingqiao Liu, Jindong Wang, Jennifer Foster, and Yue Zhang. 2023. Out-of-Distribution Generalization in Text Classification: Past, Present, and Future. ArXiv:2305.14104 [cs]. · DOI
  42. Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending Against Neural Fake News. In H. Wallach, H. Larochelle, A. Beygelz- imer, F. d\textquotesingle Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 9054-9065.
  43. Wanjun Zhong, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang, and Jian Yin. 2020. Neural Deepfake Detection with Factual Struc- ture of Text. In Proceedings of the 2020 Conference · DOI

Metadata

Authors
Cowap, A., Graham, Y., & Foster, J.
Affiliations
  • Dublin City University (IE)
  • Trinity College Dublin (IE)
ORCID
Venue
Findings of the Association for Computational Linguistics: EMNLP 2023
Publisher
Association for Computational Linguistics
Published
2023
Pages
9928-9946
DOI
10.18653/v1/2023.findings-emnlp.665
OpenAlex
W4389519013
Cited by
4
References
51
Citations by year
2026: 2 · 2025: 2
FWCI
0.71
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion, cc-by)
  • Dublin City University Open Access Institutional Repository (Dublin City University) (acceptedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
Science Foundation Ireland (18/CRT/6183)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
synthetic text detection, emotion recognition, pre-trained language models, generative AI, ChatGPT

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition. https://app.cochat.ai/papers/10.18653/v1/2023.findings-emnlp.665
The paper
Cowap, A., Graham, Y., & Foster, J. (2023). Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition. Findings of the Association for Computational Linguistics: EMNLP 2023. https://doi.org/10.18653/v1/2023.findings-emnlp.665