Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates (2312.06861v1)

Published 11 Dec 2023 in cs.CY and cs.CL

Abstract: Perception of offensiveness is inherently subjective, shaped by the lived experiences and socio-cultural values of the perceivers. Recent years have seen substantial efforts to build AI-based tools that can detect offensive language at scale, as a means to moderate social media platforms, and to ensure safety of conversational AI technologies such as ChatGPT and Bard. However, existing approaches treat this task as a technical endeavor, built on top of data annotated for offensiveness by a global crowd workforce without any attention to the crowd workers' provenance or the values their perceptions reflect. We argue that cultural and psychological factors play a vital role in the cognitive processing of offensiveness, which is critical to consider in this context. We re-frame the task of determining offensiveness as essentially a matter of moral judgment -- deciding the boundaries of ethically wrong vs. right language within an implied set of socio-cultural norms. Through a large-scale cross-cultural study based on 4309 participants from 21 countries across 8 cultural regions, we demonstrate substantial cross-cultural differences in perceptions of offensiveness. More importantly, we find that individual moral values play a crucial role in shaping these variations: moral concerns about Care and Purity are significant mediating factors driving cross-cultural differences. These insights are of crucial importance as we build AI models for the pluralistic world, where the values they espouse should aim to respect and account for moral values in diverse geo-cultural contexts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Relationship of subjective and objective social status with psychological and physiological functioning: Preliminary data in healthy, white women. Health psychology, 19(6):586.
  2. The reasonable effectiveness of diverse evaluation data.
  3. Lora Aroyo and Chris Welty. 2015. Truth is a lie: Crowd truth and the seven myths of human annotation. AI Magazine, 36(1):15–24.
  4. Morality beyond the weird: How the nomological network of morality varies across cultures. Journal of Personality and Social Psychology, 125.
  5. Training a helpful and harmless assistant with reinforcement learning from human feedback.
  6. Jack M Balkin. 2017. Digital speech and democratic culture: A theory of freedom of expression for the information society. In Law and society approaches to cyberspace, pages 325–382. Routledge.
  7. Reuben M Baron and David A Kenny. 1986. The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of personality and social psychology, 51(6):1173.
  8. Valerie C Brannon. 2019. Free speech and the regulation of social media content. Congressional Research Service, 27.
  9. The impact of culture on creativity: How cultural tightness and cultural distance affect global innovation crowdsourcing work. Administrative Science Quarterly, 60(2):189–227.
  10. European Commission. 2020. The digital services act: Ensuring a safe and accountable online environment. The Digital Services Act: Ensuring a safe and accountable online environment.
  11. Gloria Cowan and Désirée Khatchadourian. 2003. Empathy, ways of knowing, and interdependence as mediators of gender differences in attitudes toward hate speech and freedom of speech. Psychology of women quarterly, 27(4):300–308.
  12. Dealing with disagreements: Looking beyond the majority vote in subjective annotations. Transactions of the Association for Computational Linguistics, 10:92–110.
  13. Anca Dumitrache. 2015. Crowdsourcing disagreement for collecting semantic annotation. In The Semantic Web. Latest Advances and New Domains: 12th European Semantic Web Conference, ESWC 2015, Portoroz, Slovenia, May 31–June 4, 2015. Proceedings 12, pages 701–710. Springer.
  14. Large scale crowdsourcing and characterization of twitter abusive behavior. In Proceedings of the international AAAI conference on web and social media, volume 12.
  15. Handling bias in toxic speech detection: A survey. ACM Computing Surveys, 55(13s):1–32.
  16. Are we modeling the task or the annotator? an investigation of annotator bias in natural language understanding datasets. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1161–1166, Hong Kong, China. Association for Computational Linguistics.
  17. Improving alignment of dialogue agents via targeted human judgements.
  18. Is your toxicity my toxicity? exploring the impact of rater identity on toxicity annotation. Proceedings of the ACM on Human-Computer Interaction, 6(CSCW2):1–28.
  19. Moral foundations theory: The pragmatic validity of moral pluralism. In Advances in experimental social psychology, volume 47, pages 55–130. Elsevier.
  20. Liberals and conservatives rely on different sets of moral foundations. Journal of personality and social psychology, 96(5):1029.
  21. Beyond weird: Towards a broad-based behavioral science. Behavioral and brain sciences, 33(2-3):111.
  22. Challenges and strategies in cross-cultural NLP. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6997–7013, Dublin, Ireland. Association for Computational Linguistics.
  23. Geert Hofstede. 2011. Dimensionalizing cultures: The hofstede model in context. Online readings in psychology and culture, 2(1):8.
  24. Moral foundations twitter corpus: A collection of 35k tweets annotated for moral sentiment. Social Psychological and Personality Science, 11(8):1057–1071.
  25. Learning whom to trust with mace. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1120–1130.
  26. Jigsaw. 2018. Toxic comment classification challenge. Accessed: 2021-05-01.
  27. Jigsaw. 2019. Unintended bias in toxicity classification. Accessed: 2021-05-01.
  28. How do cultural differences impact the quality of sarcasm annotation?: A case study of indian annotators and american text. In Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, pages 95–99.
  29. Alignment of language agents.
  30. Confronting abusive language online: A survey from the ethical and human rights perspective. Journal of Artificial Intelligence Research, 71:431–478.
  31. Klaus Krippendorff. 2008. Systematic and random disagreement and the reliability of nominal data. Communication Methods and Measures, 2(4):323–338.
  32. MultiMedia LLC. 2023. FACT SHEET: President Biden Issues Executive Order on Safe, Secure, and Trustworthy Artificial Intelligence.
  33. Beyond western, educated, industrial, rich, and democratic (weird) psychology: Measuring and mapping scales of cultural and psychological distance. Psychological science, 31(6):678–701.
  34. Data-centric AI competition. deeplearning AI.
  35. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
  36. Annotating social media data from vulnerable populations: Evaluating disagreement between domain experts and graduate student annotators. In proceedings of the 52nd Hawaii International Conference on System Sciences.
  37. A human rights-based approach to responsible ai. arXiv preprint arXiv:2210.02667.
  38. On releasing annotator-level labels and information in datasets. In Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop, pages 133–138, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  39. Online hate ratings vary by extremes: A statistical analysis. In Proceedings of the 2019 Conference on Human Information Interaction and Retrieval, pages 213–217.
  40. Online hate interpretation varies by country, but more by individual: A statistical analysis using crowdsourced ratings. In 2018 fifth international conference on social networks analysis, management and security (snams), pages 88–94. IEEE.
  41. Why don’t you do it right? analysing annotators’ disagreement in subjective tasks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2420–2433.
  42. NLPositionality: Characterizing design biases of datasets and models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9080–9102, Toronto, Canada. Association for Computational Linguistics.
  43. Annotators with attitudes: How annotator beliefs and identities bias toxic language detection. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5884–5906, Seattle, United States. Association for Computational Linguistics.
  44. Anna Schmidt and Michael Wiegand. 2017. A survey on hate speech detection using natural language processing. In Proceedings of the fifth international workshop on natural language processing for social media, pages 1–10.
  45. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.
  46. Learning from disagreement: A survey. Journal of Artificial Intelligence Research, 72:1385–1470.
  47. Adversarial glue: A multi-task benchmark for robustness evaluation of language models.
  48. Zeerak Waseem. 2016. Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In Proceedings of the first workshop on NLP and computational social science, pages 138–142.
  49. Ex machina: Personal attacks seen at scale. In Proceedings of the 26th international conference on world wide web, pages 1391–1399.
  50. Data-centric ai: Perspectives and challenges. In Proceedings of the 2023 SIAM International Conference on Data Mining (SDM), pages 945–948. SIAM.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets