---
title: "The Relevance of Value Systems for Offensive Language Detection"
description: "This paper argues instead that whether a remark hurts often depends on the values of the person it is about. 73 references."
authors: ["Michael Wiegand", "Elisabeth Eder", "Josef Ruppenhofer"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.319/"
doi: "10.18653/v1/2026.eacl-long.319"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wiegand-2026-relevance-value-systems-offensive-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wiegand-2026-relevance-value-systems-offensive-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/52/) / The Relevance of Value Systems for Offensive Language Detection

# The Relevance of Value Systems for Offensive Language Detection

**Authors:** [Michael Wiegand](https://md.research.elamur.ai/free/en/authors/michael-wiegand/), [Elisabeth Eder](https://md.research.elamur.ai/free/en/authors/elisabeth-eder/) and [Josef Ruppenhofer](https://md.research.elamur.ai/free/en/authors/josef-ruppenhofer/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.319/) · [PDF](https://aclanthology.org/2026.eacl-long.319.pdf) · [DOI 10.18653/v1/2026.eacl-long.319](https://doi.org/10.18653/v1/2026.eacl-long.319) · [OpenAlex](https://openalex.org/W7140140853)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Most offensive language detection assumes that everyone agrees on what is offensive. This paper argues instead that whether a remark hurts often depends on the values of the person it is about. To study this, the authors built the first dataset linking offensiveness to value systems. They selected 212 controversial topics, such as guns, abortion and pornography. For each topic, they wrote neutrally worded sentences about a third-person target using 12 fixed sentence types. These types vary how strongly the target supports or opposes the topic and include intensified variants.

US-based native English speakers on Prolific labelled the sentences. Raters identified as believing Christians, conservatives, liberals or ecologically-conscious people, and imagined overhearing the remarks about a like-minded friend. The same sentence often received different labels across groups. A sentence tended to be judged offensive when it tied the target to a disliked concept or distanced them from a valued one, and the degree of engagement mattered. Classifiers trained on earlier offensive-language datasets performed poorly on this data. Only a few strong LLMs, such as GPT-5, handled it well. The work is a proof of concept for personalized content moderation.

## Key points
- The dataset has 212 topics and 2532 sentences. Of these, 1339 are offensive for at least one value system and only 152 for all four. It is publicly available with annotation guidelines at github.com/miwieg/value_systems.
- The 12 sentence types split into 6 "favouring" types (e.g. approval, practice, encourage_others_to_participate) and 6 "disfavouring" types (e.g. disapproval, no_practice, prevent_others_from_participating). Most come in plain and intensified pairs.
- A preliminary corpus study sampled 500 "accused of X" sentences from WebAsCorpus. About 40% of the accused topics were judged offensive only because of a person's value system.
- Some topics were offensive mainly to one group. Examples are casino gambling for Christians, fast fashion and eating meat for ecologically-conscious raters, and Fox News for liberals.
- An alternative dataset of sentences written spontaneously by crowdworkers proved easier to classify, because of added contextual clues and topic biases. Crowdworkers were paid $12 per hour.

*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 Vienna](https://md.research.elamur.ai/free/en/universities/university-of-vienna/) — University, Vienna, Austria · 18 works · 38,729 citations
- [FernUniversität in Hagen](https://md.research.elamur.ai/free/en/universities/fernuniversitat-in-hagen/) — University, Hagen, Germany · 2 works · 43 citations
- [Austrian Centre for Digital Humanities](https://md.research.elamur.ai/free/en/labs/austrian-centre-for-digital-humanities/) — Research institute, Vienna, Austria · 3 works · 16 citations
- [Austrian Academy of Sciences](https://md.research.elamur.ai/free/en/government/austrian-academy-of-sciences/) — Government body, Vienna, Austria · 2 works

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Communication](https://md.research.elamur.ai/free/en/shelves/social-sciences/communication/) · 104 works

🧭 Topics (1): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works

## Cite

Cite as: Michael Wiegand, Elisabeth Eder and Josef Ruppenhofer. 2026. The Relevance of Value Systems for Offensive Language Detection. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wiegand2026relevance,
  title = {{The Relevance of Value Systems for Offensive Language Detection}},
  author = {Michael Wiegand, Elisabeth Eder and Josef Ruppenhofer},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.319},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.319}
}
```

- [← previous The Prosody of Emojis](https://md.research.elamur.ai/free/en/papers/zhou-2026-prosody-emojis/)
- [next → The Reliability Illusion in Synthetic Patients: Psychometric Misalignment of Open-weight LLMs on PHQ-9 and GAD-7](https://md.research.elamur.ai/free/en/papers/shen-2026-reliability-illusion-synthetic-patients-psychometric/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/52/)

## References

73 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. [FLAIR: An easy-to-use framework for state-of-the-art NLP](https://md.research.elamur.ai/free/en/papers/akbik-2019-flair-easy-use-framework-state/). In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL), pages 54–59, Minneapolis, MN…
2. Yu, Wentao Zhang, X. Q. Li, Xiangyue Jin, Xianzu Wang, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaojin Shen, Xiaokang Chen, Xiaokang Zhang, Xiaosha Chen, Xiaotao Nie, Xiaowen Sun, Xiaoxiang Wang, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xingkai Yu, Xinnan Song, Xinxia Shan, Xinyi Zhou, Xinyu Yang, Xi… [find](https://scholar.google.com/scholar?q=Yu%2C+Wentao+Zhang%2C+X%2E+Q%2E+Li%2C+Xiangyue+Jin%2C+Xianzu+Wang%2C+Xiao+Bi%2C+Xiaodong+Liu%2C+Xiaohan+Wang%2C+Xiaojin+Shen%2C+Xiaokang+Chen%2C+Xiaokang+Zhang%2C+Xiaosha+Chen%2C+Xiaotao+Nie%2C+Xiaowen+Sun%2C+Xiaoxiang+Wang%2C+Xin+Che)
3. Bob Altemeyer and Bruce Hunsberger. 2009. Authoritarianism, Religious Fundamentalism, Quest, and Prejudice. The International Journal for the Psychology of Religion, 2(2):113–133. [find](https://scholar.google.com/scholar?q=Bob+Altemeyer+and+Bruce+Hunsberger%2E+2009%2E+Authoritarianism%2C+Religious+Fundamentalism%2C+Quest%2C+and+Prejudice%2E+The+International+Journal+for+the+Psychology+of+Religion%2C+2%282%29%3A113%E2%80%93133%2E)
4. Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, and Vasudeva Varma. 2017. Deep Learning for Hate Speech Detection in Tweets. In Proceedings of the International Conference on World Wide Web (WWW), pages 759–760, Perth, Australia. [find](https://scholar.google.com/scholar?q=Pinkesh+Badjatiya%2C+Shashank+Gupta%2C+Manish+Gupta%2C+and+Vasudeva+Varma%2E+2017%2E+Deep+Learning+for+Hate+Speech+Detection+in+Tweets%2E+In+Proceedings+of+the+International+Conference+on+World+Wide+Web+%28WWW%29%2C+pa)
5. Marco Baroni, Silvia Bernardini, Adriano Ferraresi, and Eros Zanchetti. 2009. The WaCky Wide Web: A Collection of Very Large Linguistically Processed Web-Crawled Corpora. Language Resources and Evaluation, 43(3):209–226. [find](https://scholar.google.com/scholar?q=Marco+Baroni%2C+Silvia+Bernardini%2C+Adriano+Ferraresi%2C+and+Eros+Zanchetti%2E+2009%2E+The+WaCky+Wide+Web%3A+A+Collection+of+Very+Large+Linguistically+Processed+Web%2DCrawled+Corpora%2E+Language+Resources+and+Evalua)
6. Berta Chulvi, Lara Fontanella, Roberto Labadie-Tamayo, and Paolo Rosso. 2023. Social or Individual Disagreement? Perspectivism in the Annotation of Sexist Jokes. In Proceedings of the Workshop on Perspectivist Approaches to NLP, Kraków, Poland. [find](https://scholar.google.com/scholar?q=Berta+Chulvi%2C+Lara+Fontanella%2C+Roberto+Labadie%2DTamayo%2C+and+Paolo+Rosso%2E+2023%2E+Social+or+Individual+Disagreement%3F+Perspectivism+in+the+Annotation+of+Sexist+Jokes%2E+In+Proceedings+of+the+Workshop+on+Pers)
7. Pamela Johnston Conover and Stanley Feldman. 1981. The Origins and Meaning of Liberal/Conservative Self-Identifications. American Journal of Political Science, 25(4):617–645. [find](https://scholar.google.com/scholar?q=Pamela+Johnston+Conover+and+Stanley+Feldman%2E+1981%2E+The+Origins+and+Meaning+of+Liberal%2FConservative+Self%2DIdentifications%2E+American+Journal+of+Political+Science%2C+25%284%29%3A617%E2%80%93645%2E)
8. Lingjia Deng, Yoonjung Choi, and Janyce Wiebe. 2013. Benefactive/Malefactive Event and Writer Attitude Annotation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 120–125, Sofia, Bulgaria. [find](https://scholar.google.com/scholar?q=Lingjia+Deng%2C+Yoonjung+Choi%2C+and+Janyce+Wiebe%2E+2013%2E+Benefactive%2FMalefactive+Event+and+Writer+Attitude+Annotation%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Association+for+Computational+Linguistics)
9. Aida Mostafazadeh Davani, Mohammad Atari, Brendan Kennedy, and Morteza Dehghani. 2022. [Hate Speech Classifiers Learn Normative Social Stereotypes](https://md.research.elamur.ai/free/en/papers/davani-2023-hate-speech-classifiers-learn-normative/). Transactions of the Association for Computational Linguistics (TACL), 11:300–319.
10. Haibo Ding and Ellen Riloff. 2018. Weakly Super-vsied Induction of Affective Events by Optimizing Semantic Consistency. In Proceedings of the National Conference on Artificial Intelligence (AAAI), pages 5763–5770, New Orleans, LA, USA. [find](https://scholar.google.com/scholar?q=Haibo+Ding+and+Ellen+Riloff%2E+2018%2E+Weakly+Super%2Dvsied+Induction+of+Affective+Events+by+Optimizing+Semantic+Consistency%2E+In+Proceedings+of+the+National+Conference+on+Artificial+Intelligence+%28AAAI%29%2C+pag)
11. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, H… — [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://md.research.elamur.ai/free/en/papers/elsherief-2021-latent-hatred-benchmark-understanding-implicit/)
12. Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. LIBLINEAR: A Library for Large Linear Classification. Journal of Machine Learning Research, 9:1871–1874. [find](https://scholar.google.com/scholar?q=Rong%2DEn+Fan%2C+Kai%2DWei+Chang%2C+Cho%2DJui+Hsieh%2C+Xiang%2DRui+Wang%2C+and+Chih%2DJen+Lin%2E+2008%2E+LIBLINEAR%3A+A+Library+for+Large+Linear+Classification%2E+Journal+of+Machine+Learning+Research%2C+9%3A1871%E2%80%931874%2E)
13. Eve Fleisig, Rediet Abebe, and Dan Klein. 2023. When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6715–6726, Singapore. [find](https://scholar.google.com/scholar?q=Eve+Fleisig%2C+Rediet+Abebe%2C+and+Dan+Klein%2E+2023%2E+When+the+Majority+is+Wrong%3A+Modeling+Annotator+Disagreement+for+Subjective+Tasks%2E+In+Proceedings+of+the+Conference+on+Empirical+Methods+in+Natural+Langu)
14. Paula Fortuna and Sérgio Nunes. 2018. A Survey on Automatic Detection of Hate Speech in Text. ACM Computing Surveys, 51(4):85:1–85:30. [find](https://scholar.google.com/scholar?q=Paula+Fortuna+and+S%C3%A9rgio+Nunes%2E+2018%2E+A+Survey+on+Automatic+Detection+of+Hate+Speech+in+Text%2E+ACM+Computing+Surveys%2C+51%284%29%3A85%3A1%E2%80%9385%3A30%2E)
15. Antigoni-Maria Founta, Constantinos Djouvas, Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Gianluca Stringhini, Athena Vakali, Michael Sirivianos, and Nicolas Kourtellis. 2018. Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior. In Proceedings of the International A… [find](https://scholar.google.com/scholar?q=Antigoni%2DMaria+Founta%2C+Constantinos+Djouvas%2C+Despoina+Chatzakou%2C+Ilias+Leontiadis%2C+Jeremy+Blackburn%2C+Gianluca+Stringhini%2C+Athena+Vakali%2C+Michael+Sirivianos%2C+and+Nicolas+Kourtellis%2E+2018%2E+Large+Scale+C)
16. Gallup. 2023. How Religious Are Americans? [https://news.gallup.com/poll/358364/reli](https://news.gallup.com/poll/358364/reli) gious-americans.aspx. Accessed: 26-Aug-2024. [↗](https://news.gallup.com/poll/358364/reli)
17. Gallup. 2024. Church Attendance Has Declined in Most U.S. Religious Groups. [https://news.gallu](https://news.gallu) p.com/poll/642548/church-attendanc e-declined- religious-groups.aspx. Accessed: 27-Aug-2024. [↗](https://news.gallu)
18. Lei Gao and Ruihong Huang. 2017. Detecting Online Hate Speech Using Context Aware Models. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP), pages 260–266, Varna, Bulgaria. [find](https://scholar.google.com/scholar?q=Lei+Gao+and+Ruihong+Huang%2E+2017%2E+Detecting+Online+Hate+Speech+Using+Context+Aware+Models%2E+In+Proceedings+of+the+International+Conference+Recent+Advances+in+Natural+Language+Processing+%28RANLP%29%2C+pages+2)
19. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/). In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 33…
20. Pengcheng Hea, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In International Conference on Learning Representations.
21. Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, and Jacob Steinhardt. 2021. [Aligning AI with Shared Human Values](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-aligning-ai-shared-human-values/). In Proceedings of the International Conference on Learning Representations (ICLR), Virtual Event, Austria.
22. Joe Hoover, Gwenyth Portillo-Wightman, Leigh Yeh, Shreya Havaldar, Aida Mostafazadeh, Ying Lin, Davani, Brendan Kennedy, Mohammad Atari, Zahra Kamel, Madelyn Mendlen, Gabriela Moreno, Christina Park, Tingyee E. Chang, Jenna Chin, Christian Leung, Jun Yen Leung, Arineh Mirinjian, and Morteza Dehghani… [find](https://scholar.google.com/scholar?q=Joe+Hoover%2C+Gwenyth+Portillo%2DWightman%2C+Leigh+Yeh%2C+Shreya+Havaldar%2C+Aida+Mostafazadeh%2C+Ying+Lin%2C+Davani%2C+Brendan+Kennedy%2C+Mohammad+Atari%2C+Zahra+Kamel%2C+Madelyn+Mendlen%2C+Gabriela+Moreno%2C+Christina+Park%2C+)
23. Mohit Iyyer, Peter Enns, Jordan Boyd-Graber, and Philip Resnik. 2014. Politicial Ideology Detection Using Recursive Neural Networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 1113–1122, Baltimore, MD, USA. [find](https://scholar.google.com/scholar?q=Mohit+Iyyer%2C+Peter+Enns%2C+Jordan+Boyd%2DGraber%2C+and+Philip+Resnik%2E+2014%2E+Politicial+Ideology+Detection+Using+Recursive+Neural+Networks%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Association+for+Computa)
24. Shagun Jhaver, Alice Qian Zhang, Quan Ze Chen, Nikhila Natarajan, Ruotong Wang, and Amy X. Zhang. 2023. Personalizing Content Moderation on Social Media: User Perspectives on Moderation Choices, Interface Design, and Labor. In Proceedings of the ACM on Human-Computer Interaction, volume 7, pages 1–3… [find](https://scholar.google.com/scholar?q=Shagun+Jhaver%2C+Alice+Qian+Zhang%2C+Quan+Ze+Chen%2C+Nikhila+Natarajan%2C+Ruotong+Wang%2C+and+Amy+X%2E+Zhang%2E+2023%2E+Personalizing+Content+Moderation+on+Social+Media%3A+User+Perspectives+on+Moderation+Choices%2C+Inter)
25. Daniel Kahneman, Olivier Sibony, and Cass R. Sunstein. 2021. Noise: A Flaw in Human Judgment. Little, Brown and Company. [find](https://scholar.google.com/scholar?q=Daniel+Kahneman%2C+Olivier+Sibony%2C+and+Cass+R%2E+Sunstein%2E+2021%2E+Noise%3A+A+Flaw+in+Human+Judgment%2E+Little%2C+Brown+and+Company%2E)
26. Kamil Kanclerz, Marcin Gruza, Konrad Karanowski, Julita Bielaniewicz, Piotr Milkowski, Jan Kocon, and Przemyslaw Kazienko. 2022. What if Ground Tuth is Subjective? Personalized Deep Neural Hate Speech Detection. In Proceedings of the Workshop on Perspectivist Approaches to NLP, pages 37–45, Marseill… [find](https://scholar.google.com/scholar?q=Kamil+Kanclerz%2C+Marcin+Gruza%2C+Konrad+Karanowski%2C+Julita+Bielaniewicz%2C+Piotr+Milkowski%2C+Jan+Kocon%2C+and+Przemyslaw+Kazienko%2E+2022%2E+What+if+Ground+Tuth+is+Subjective%3F+Personalized+Deep+Neural+Hate+Speech)
27. Brendan Kennedy, Preni Golazizian, Jackson Trager Mohammad Atari, Joe Hoover, Aida Mostafazadeh Davani, and Morteza Dehghani. 2023. The (moral) language of hate. PNAS Nexus, 2:1–16. [find](https://scholar.google.com/scholar?q=Brendan+Kennedy%2C+Preni+Golazizian%2C+Jackson+Trager+Mohammad+Atari%2C+Joe+Hoover%2C+Aida+Mostafazadeh+Davani%2C+and+Morteza+Dehghani%2E+2023%2E+The+%28moral%29+language+of+hate%2E+PNAS+Nexus%2C+2%3A1%E2%80%9316%2E)
28. Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://md.research.elamur.ai/free/en/papers/kiela-2020-hateful-memes-challenge-detecting-hate/). In Advances in Neural Information Processing Systems, volume 33, pages 2611–2624, Vancouver, Canada.
29. Dilek Küçük and Fazli Can. 2020. Stance Detection: A Survey. ACM Computing Surveys, 53(1):12:1–12:37. [find](https://scholar.google.com/scholar?q=Dilek+K%C3%BC%C3%A7%C3%BCk+and+Fazli+Can%2E+2020%2E+Stance+Detection%3A+A+Survey%2E+ACM+Computing+Surveys%2C+53%281%29%3A12%3A1%E2%80%9312%3A37%2E)
30. Md Tahmid Rahman Laskar, M Saiful Bari, Mizanur Rahman, Md Amran Hossen Bhuiyan, Shafiq Joty, and Jimmy Huang. 2023. [A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets](https://md.research.elamur.ai/free/en/papers/laskar-2023-systematic-study-comprehensive-evaluation-chatgpt/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 431– 469, Toronto, Cana…
31. Nayeon Lee, Chani Jung, Junho Myung, Jiho Jin, Jose Camacho-Collados, Juho Kim, and Alice Oh. 2024. Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis. In Proceedings of the 2024 Conference of the North American Chapter of the Association f… [find](https://scholar.google.com/scholar?q=Nayeon+Lee%2C+Chani+Jung%2C+Junho+Myung%2C+Jiho+Jin%2C+Jose+Camacho%2DCollados%2C+Juho+Kim%2C+and+Alice+Oh%2E+2024%2E+Exploring+Cross%2DCultural+Differences+in+English+Hate+Speech+Annotations%3A+From+Dataset+Construction+t)
32. Enrico Liscio, Oscar Araque, Lorenzo Gatti, Ionut Constantinescu, Catholijn Jonker, Kyriaki Kalimeri, and Pradeep Kumar Murukannaiah. 2023. What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric. In Proceedings of the Annual Meeting of t… [find](https://scholar.google.com/scholar?q=Enrico+Liscio%2C+Oscar+Araque%2C+Lorenzo+Gatti%2C+Ionut+Constantinescu%2C+Catholijn+Jonker%2C+Kyriaki+Kalimeri%2C+and+Pradeep+Kumar+Murukannaiah%2E+2023%2E+What+does+a+Text+Classifier+Learn+about+Morality%3F+An+Explain)
33. Enrico Liscio, Alin Dondera, Andrei Geadau, Catholijn Jonker, and Pradeep Murukannaiah. 2022. Cross-Domain Classification of Moral Values. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2727–2745, Seattle, WA, USA. [find](https://scholar.google.com/scholar?q=Enrico+Liscio%2C+Alin+Dondera%2C+Andrei+Geadau%2C+Catholijn+Jonker%2C+and+Pradeep+Murukannaiah%2E+2022%2E+Cross%2DDomain+Classification+of+Moral+Values%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
34. 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](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
35. Steven Ludeke, Wendy Johnson, and Thomas J. Bouchard Jr. 2013. “Obedience to traditional authority:” a heritable factor underlying authoritarianism, conservatism and religiousness. Personality and Individual Differences, 55(4):375–380. [find](https://scholar.google.com/scholar?q=Steven+Ludeke%2C+Wendy+Johnson%2C+and+Thomas+J%2E+Bouchard+Jr%2E+2013%2E+%E2%80%9CObedience+to+traditional+authority%3A%E2%80%9D+a+heritable+factor+underlying+authoritarianism%2C+conservatism+and+religiousness%2E+Personality+and+Ind)
36. Gregory R. Maio, James M. Olsen, Mark M. Bernard, and Michelle A. Luke. 2003. Ideologies, Values, Attitudes, and Behavior. In John DeLamater, editor, Handbook of Ssocial Psychology, pages 283–308. Kluwer Academic/Plenum Publishers. [find](https://scholar.google.com/scholar?q=Gregory+R%2E+Maio%2C+James+M%2E+Olsen%2C+Mark+M%2E+Bernard%2C+and+Michelle+A%2E+Luke%2E+2003%2E+Ideologies%2C+Values%2C+Attitudes%2C+and+Behavior%2E+In+John+DeLamater%2C+editor%2C+Handbook+of+Ssocial+Psychology%2C+pages+283%E2%80%93308%2E+Klu)
37. Mary L. McHugh. 2012. Interrater reliability: the kappa statistic. Biochemia Medica, 22(3):276–282. [find](https://scholar.google.com/scholar?q=Mary+L%2E+McHugh%2E+2012%2E+Interrater+reliability%3A+the+kappa+statistic%2E+Biochemia+Medica%2C+22%283%29%3A276%E2%80%93282%2E)
38. Douglas M. McLeod, Benjamin H. Detenber, and William P. Eveland Jr. 2001. Behind the Third-Person Effect: Differentiating Perceptual Processes for Self and Other. Journal of Communication, 51(4):678–695. [find](https://scholar.google.com/scholar?q=Douglas+M%2E+McLeod%2C+Benjamin+H%2E+Detenber%2C+and+William+P%2E+Eveland+Jr%2E+2001%2E+Behind+the+Third%2DPerson+Effect%3A+Differentiating+Perceptual+Processes+for+Self+and+Other%2E+Journal+of+Communication%2C+51%284%29%3A678%E2%80%936)
39. Julia Mendelsohn, Rona Le Bras, Yejin Choi, and Maarten Sap. 2023. From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 15162–15180, Toronto, Canada. [find](https://scholar.google.com/scholar?q=Julia+Mendelsohn%2C+Rona+Le+Bras%2C+Yejin+Choi%2C+and+Maarten+Sap%2E+2023%2E+From+Dogwhistles+to+Bullhorns%3A+Unveiling+Coded+Rhetoric+with+Language+Models%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Association)
40. Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, and Colin Cherry. 2016. [SemEval-2016 Task 6: Detecting Stance in Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2016-semeval-2016-task-6-detecting/). In Proceedings of the International Workshop on Semantic Evaluation (SemEval), pages 31–41, San Diego, CA, USA.
41. Fabio Motoki, Valdemar Pinho Neto, and Victor Rodrigues. 2023. More human than human: measuring ChatGPT political bias. Public Choice. [find](https://scholar.google.com/scholar?q=Fabio+Motoki%2C+Valdemar+Pinho+Neto%2C+and+Victor+Rodrigues%2E+2023%2E+More+human+than+human%3A+measuring+ChatGPT+political+bias%2E+Public+Choice%2E)
42. Chikashi Nobata, Joel Tetreault, Achint Thomas, Yashar Mehdad, and Yi Chang. 2016. Abusive Language Detection in Online User Content. In Proceedings of the International Conference on World Wide Web (WWW), pages 145–153, Republic and Canton of Geneva, Switzerland. [find](https://scholar.google.com/scholar?q=Chikashi+Nobata%2C+Joel+Tetreault%2C+Achint+Thomas%2C+Yashar+Mehdad%2C+and+Yi+Chang%2E+2016%2E+Abusive+Language+Detection+in+Online+User+Content%2E+In+Proceedings+of+the+International+Conference+on+World+Wide+Web+%28)
43. Nicolas Ocampo, Ekaterina Sviridova, Elena Cabrio, and Serena Villata. 2023. An In-depth Analysis of Implicit and Subtle Hate Speech Messages. In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL), pages 1989–2005, Dubrovnik, Croatia. [find](https://scholar.google.com/scholar?q=Nicolas+Ocampo%2C+Ekaterina+Sviridova%2C+Elena+Cabrio%2C+and+Serena+Villata%2E+2023%2E+An+In%2Ddepth+Analysis+of+Implicit+and+Subtle+Hate+Speech+Messages%2E+In+Proceedings+of+the+Conference+on+European+Chapter+of+t)
44. Myle Ott, Yejin Choi, Claire Cardie, and Jeffrey T. Hancock. 2011. [Finding Deceptive Opinion Spam by Any Stretch of the Imagination](https://md.research.elamur.ai/free/en/papers/ott-2011-finding-deceptive-opinion-spam-any/). In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 309—-319, Portland, OR, USA.
45. John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon, Nithum Thain, and Ion Androutsopoulos. 2020. Toxity Detection: Does Context Really Matter? In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 4296–4305, Online. [find](https://scholar.google.com/scholar?q=John+Pavlopoulos%2C+Jeffrey+Sorensen%2C+Lucas+Dixon%2C+Nithum+Thain%2C+and+Ion+Androutsopoulos%2E+2020%2E+Toxity+Detection%3A+Does+Context+Really+Matter%3F+In+Proceedings+of+the+Annual+Meeting+of+the+Association+for+)
46. Pew Research Center. 2014a. The Religious Landscape Study: Political ideology among Christians. [https://www.pewresearch.org/religious-l](https://www.pewresearch.org/religious-l) andscape-study/\#political-ideology. Accessed: 26-Aug-2024. [↗](https://www.pewresearch.org/religious-l)
47. Pew Research Center. 2014b. The Religious Landscape Study: Views about environmental regulation among Christians. [https://www.pewresearch.or](https://www.pewresearch.or) g/religious-landscape-study/\#view s-about-environmental-regulation. Accessed: 26-Aug-2024. [↗](https://www.pewresearch.or)
48. Pew Research Center. 2023. How Americans View Future Harms From Climate Change in Their Community and Around the U.S. [https://www.pe](https://www.pe) wresearch.org/science/2023/10/25/h ow-americans-view-future-harms-fro m-climate-change-in-their-communi ty-and-around-the-u-s/ps_2023-10-2 5_climate-change-harms_00-02… [↗](https://www.pe)
49. Flor Miriam Plaza-del-arco, Debora Nozza, and Dirk Hovy. 2023. Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech. In Proceedings of the Workshop on Online Abuase and Harms (WOAH), pages 60–68, Toronto, Canada. [find](https://scholar.google.com/scholar?q=Flor+Miriam+Plaza%2Ddel%2Darco%2C+Debora+Nozza%2C+and+Dirk+Hovy%2E+2023%2E+Respectful+or+Toxic%3F+Using+Zero%2DShot+Learning+with+Language+Models+to+Detect+Hate+Speech%2E+In+Proceedings+of+the+Workshop+on+Online+Abuase)
50. Martin Potthast, Benno Stein, Alberto Barrón-Cedeño, and Paolo Rosso. 2010. An Evaluation Framework for Plagiarism Detection. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 997–1005, Beijing, China. [find](https://scholar.google.com/scholar?q=Martin+Potthast%2C+Benno+Stein%2C+Alberto+Barr%C3%B3n%2DCede%C3%B1o%2C+and+Paolo+Rosso%2E+2010%2E+An+Evaluation+Framework+for+Plagiarism+Detection%2E+In+Proceedings+of+the+International+Conference+on+Computational+Linguistic)
51. Ines Reinig, Maria Becker, Ines Rehbein, and Simone Ponzetto. 2024. A Survey on Modelling Morality for Text Analysis. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4136– 4155, Bangkok, Thailand. [find](https://scholar.google.com/scholar?q=Ines+Reinig%2C+Maria+Becker%2C+Ines+Rehbein%2C+and+Simone+Ponzetto%2E+2024%2E+A+Survey+on+Modelling+Morality+for+Text+Analysis%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+pages+4136)
52. Hannah Ritchie. 2024. More people care about climate change than you think. Our World in Data. [https://archive.ourworldindata.org/20251](https://archive.ourworldindata.org/20251) 209-133038/climate-change-support .html. [↗](https://archive.ourworldindata.org/20251)
53. Hernando Rojas, Dhavan V. Shah, and Ronald J. Faber. 1996. For the Good of Others: Censorship and the Third-Person Effect. International Journal of Public Opinion Research, 8(2):163–186. [find](https://scholar.google.com/scholar?q=Hernando+Rojas%2C+Dhavan+V%2E+Shah%2C+and+Ronald+J%2E+Faber%2E+1996%2E+For+the+Good+of+Others%3A+Censorship+and+the+Third%2DPerson+Effect%2E+International+Journal+of+Public+Opinion+Research%2C+8%282%29%3A163%E2%80%93186%2E)
54. Milton Rokeach. 1973. The Nature of Human Values. Free Press. [find](https://scholar.google.com/scholar?q=Milton+Rokeach%2E+1973%2E+The+Nature+of+Human+Values%2E+Free+Press%2E)
55. Paul Rottger, Bertie Vidgen, Dirk Hovy, and Janet Pierrehumbert. 2022. [Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks](https://md.research.elamur.ai/free/en/papers/rottger-2022-two-contrasting-data-annotation-paradigms/). In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL), pages 175–190, Seattle, WA, USA.
56. Xia Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zhengxu Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, and Thomas Scialom. 2023. [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/).
57. Paul Röttger, Bertram Vidgen, Dong Nguyen, Zeerak Waseem, Helen Margetts, and Janet B. Pierrehumbert. 2021. [HateCheck: Functional Tests for Hate Speech Detection Models](https://md.research.elamur.ai/free/en/papers/rottger-2021-hatecheck-functional-tests-hate-speech/). In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 41–58, Online.
58. Betty van Aken, Julian Risch, Ralf Krestel, and Alexander Löser. 2018. [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://md.research.elamur.ai/free/en/papers/aken-2018-challenges-toxic-comment-classification-depth/). In Proceedings of the Workshop on Abusive Language Online (ALW), pages 33–42, Brussels, Belgium.
59. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. [Whose opinions do language models reflect?](https://md.research.elamur.ai/free/en/papers/santurkar-2023-whose-opinions-language-models-reflect/) In Proceedings of the International Conference on Machine Learning (ICML), pages 29971–30004, Hawaii, HI, USA.
60. Bertie Vidgen, Tristan Thrush, Zeerak Waseem, and Douwe Kiela. 2021. [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/). In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 1667–1682, Online.
61. Maarten Sap, Swapna Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, and Noah A. Smith. 2022. [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://md.research.elamur.ai/free/en/papers/sap-2022-annotators-attitudes-how-annotator-beliefs/). In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAAC…
62. Zeerak Waseem, Thomas Davidson, Dana Warmsley, and Ingmar Weber. 2017. [Understanding Abuse: A Typology of Abusive Language Detection Subtasks](https://md.research.elamur.ai/free/en/papers/waseem-2017-understanding-abuse-typology-abusive-language/). In Proceedings of the ACL-Workshop on Abusive Language Online, pages 78–84, Vancouver, BC, Canada.
63. Shalom H. Schwartz. 1992. Universals in the Content and Structure of Values: Theoretical Advances and Empirical Tests in 20 Countries. Advances in Experimental Social Psychology, 25:1–65. [find](https://scholar.google.com/scholar?q=Shalom+H%2E+Schwartz%2E+1992%2E+Universals+in+the+Content+and+Structure+of+Values%3A+Theoretical+Advances+and+Empirical+Tests+in+20+Countries%2E+Advances+in+Experimental+Social+Psychology%2C+25%3A1%E2%80%9365%2E)
64. Qinlan Shen and Carolyn Rose. 2021. What Sounds “Right” to Me? Experiential Factors in the Perception of Political Ideology". In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL), pages 1762– 1771, Online. [find](https://scholar.google.com/scholar?q=Qinlan+Shen+and+Carolyn+Rose%2E+2021%2E+What+Sounds+%E2%80%9CRight%E2%80%9D+to+Me%3F+Experiential+Factors+in+the+Perception+of+Political+Ideology%22%2E+In+Proceedings+of+the+Conference+on+European+Chapter+of+the+Association+fo)
65. Mark Spranca, Elisa Minsk, and Jonathan Baron. 1991. Omission and commission in judgment and choice. Journal of Experimental Social Psychology, 27(1):76– 105. [find](https://scholar.google.com/scholar?q=Mark+Spranca%2C+Elisa+Minsk%2C+and+Jonathan+Baron%2E+1991%2E+Omission+and+commission+in+judgment+and+choice%2E+Journal+of+Experimental+Social+Psychology%2C+27%281%29%3A76%E2%80%93+105%2E)
66. Judith Jarvis Thomson. 1976. Killing, Letting Die, and the Trolley Problem. The Monist, 59(2):204–217. [find](https://scholar.google.com/scholar?q=Judith+Jarvis+Thomson%2E+1976%2E+Killing%2C+Letting+Die%2C+and+the+Trolley+Problem%2E+The+Monist%2C+59%282%29%3A204%E2%80%93217%2E)
67. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, D. Bikel, Lukas Blecher, Cristian Cantón Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fulle… — [Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter](https://md.research.elamur.ai/free/en/papers/waseem-2016-hateful-symbols-or-hateful-people/)
68. Tharindu Weerasooriya, Sujan Dutta, Tharindu Ranasinghe, Marcos Zampieri, Christopher Homan, and Ashiqur KhudaBukhsh. 2023. Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive. In Proceedings of the Conference on Empirical M… [find](https://scholar.google.com/scholar?q=Tharindu+Weerasooriya%2C+Sujan+Dutta%2C+Tharindu+Ranasinghe%2C+Marcos+Zampieri%2C+Christopher+Homan%2C+and+Ashiqur+KhudaBukhsh%2E+2023%2E+Vicarious+Offense+and+Noise+Audit+of+Offensive+Speech+Classifiers%3A+Unifying+)
69. Michael Wiegand, Elisabeth Eder, and Josef Ruppenhofer. 2022. Identifying Implicitly Abusive Remarks about Identity Groups using a Linguistically Informed Approach. In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL), pages 5600– 5612, Seat… [find](https://scholar.google.com/scholar?q=Michael+Wiegand%2C+Elisabeth+Eder%2C+and+Josef+Ruppenhofer%2E+2022%2E+Identifying+Implicitly+Abusive+Remarks+about+Identity+Groups+using+a+Linguistically+Informed+Approach%2E+In+Proceedings+of+the+Human+Languag)
70. Michael Wiegand, Maja Geulig, and Josef Ruppenhofer. 2021a. Implicitly Abusive Comparisons – A New Dataset and Linguistic Analysis. In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL), pages 358–368, Online. [find](https://scholar.google.com/scholar?q=Michael+Wiegand%2C+Maja+Geulig%2C+and+Josef+Ruppenhofer%2E+2021a%2E+Implicitly+Abusive+Comparisons+%E2%80%93+A+New+Dataset+and+Linguistic+Analysis%2E+In+Proceedings+of+the+Conference+on+European+Chapter+of+the+Associat)
71. Michael Wiegand, Josef Ruppenhofer, and Elisabeth Eder. 2021b. Implicitly Abusive Language – What does it actually look like and why are we not getting there? In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL), pages 576–587, Online. [find](https://scholar.google.com/scholar?q=Michael+Wiegand%2C+Josef+Ruppenhofer%2C+and+Elisabeth+Eder%2E+2021b%2E+Implicitly+Abusive+Language+%E2%80%93+What+does+it+actually+look+like+and+why+are+we+not+getting+there%3F+In+Proceedings+of+the+Human+Language+Tech)
72. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… — [Qwen3 Technical Report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/)
73. Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar. 2019. [Predicting the Type and Target of Offensive Posts in Social Media](https://md.research.elamur.ai/free/en/papers/zampieri-2019-predicting-type-target-offensive-posts/). In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL), pages 1415–1420, M…

*Updated 2 November 2026*