CoChat
Sign Up
Cited by 169Psychology of Moral and Emotional JudgmentTopic ModelingSentiment Analysis and Opinion Mining

Social chemistry 101: Learning to reason about social and moral norms

Open access
Forbes, Maxwell, Hwang, Jena D., Shwartz, Vered, Sap, Maarten, Choi, Yejin·2020·Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
DOI 10.18653/v1/2020.emnlp-main.48
Open this paper in CoChat — free accountOpen PDF

Abstract

Social norms-the unspoken commonsense rules about acceptable social behavior-are crucial in understanding the underlying causes and intents of people's actions in narratives.For example, underlying an action such as "wanting to call cops on my neighbor" are social norms that inform our conduct, such as "It is expected that you report crimes."We present SOCIAL CHEMISTRY, a new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language.We introduce SOCIAL-CHEM-101, a large-scale corpus that catalogs 292k rules-of-thumb such as "It is rude to run a blender at 5am" as the basic conceptual units.Each rule-of-thumb is further broken down with 12 different dimensions of people's judgments, including social judgments of good and bad, moral foundations, expected cultural pressure, and assumed legality, which together amount to over 4.5 million annotations of categorical labels and free-text descriptions.Comprehensive empirical results based on state-of-the-art neural models demonstrate that computational modeling of social norms is a promising research direction.Our model framework, NEURAL NORM TRANSFORMER, learns and generalizes SOCIAL-CHEM-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb.Punching a friend who stole from me.RoT 1: It is unacceptable to injure a person.RoT 2: People should not steal from others.RoT 3: It is bad to betray a friend.RoT 4: It is OK to want to take revenge.

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/v1/2020.emnlp-main.48

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

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?

  • Data generation derived from crowdsourcing may favor majority opinions.

    “Data generation derived from crowdsourcing, for instance, may favor majority opinions, as Kim et al. (2022) point out in their creation of an inherently subjective social norm dataset, based on the Social Chemistry dataset that Forbes et al. (2020) acknowledge to represent primarily English-speaking, North American norms.”

    From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Forbes et al. 2020

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 32

  1. George J Bowdery. 1941. Conventions and norms. Phi- losophy of Science, 8(4):493-505.
  2. Haibo Ding and Ellen Riloff. 2016. Acquiring knowl- edge of affective events from blogs using label prop- agation. In AAAI.
  3. Jennifer L Eberhardt. 2020. Biased: Uncovering the hidden prejudice that shapes what we see, think, and do. Penguin Books.
  4. Jon Elster. 2006. Fairness and norms. Social Research, pages 365-376.
  5. Charles J Fillmore and Collin F Baker. 2001. Frame semantics for text understanding. In Proceedings of WordNet and Other Lexical Resources Workshop, NAACL, volume 6.
  6. Dean Fulgoni, Jordan Carpenter, Lyle Ungar, and Daniel Preot ¸iuc-Pietro. 2016. An empirical explo- ration of moral foundations theory in partisan news sources. In LREC, pages 3730-3736.
  7. Jesse Graham, Jonathan Haidt, and Brian A Nosek. 2009. Liberals and conservatives rely on different sets of moral foundations. J. Pers. Soc. Psychol., 96(5):1029-1046.
  8. Herbert P Grice. 1975. Logic and conversation. In Speech acts, pages 41-58. Brill.
  9. Jonathan Haidt, Silvia Helena Koller, and Maria G Dias. 1993. Affect, culture, and morality, or is it wrong to eat your dog? Journal of personality and social psychology, 65(4):613.
  10. Richard Mervyn Hare, Richard Mervyn Hare, Richard Mervyn Hare Hare, and Richard M Hare. 1981. Moral thinking: Its levels, method, and point. Ox- ford: Clarendon Press; New York: Oxford Univer- sity Press.
  11. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text de- generation. In International Conference on Learn- ing Representations.
  12. Lawrence Kohlberg. 1976. Moral stages and moraliza- tion. Moral development and behavior, pages 31- 53.
  13. Nicholas Lourie, Ronan Le Bras, and Yejin Choi. 2020. Scruples: A corpus of community ethical judgments on 32,000 real-life anecdotes. arXiv e-prints.
  14. Bertram F Malle, Steve Guglielmo, and Andrew E Monroe. 2014. A theory of blame. Psychological Inquiry, 25(2):147-186.
  15. Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A cor- pus and cloze evaluation for deeper understanding of commonsense stories. In NAACL, pages 839- 849, San Diego, California. Association for Com- putational Linguistics. Corpus available at https: //cs.rochester.edu/nlp/rocstories/. · DOI · Paper page
  16. J Nørregaard, B D Horne, and S Adalı. 2019. NELA- GT-2018: A large multi-labelled news dataset for the study of misinformation in news articles. In AAAI. wvvw.aaai.org.
  17. H Wesley Perkins and Alan D Berkowitz. 1986. Per- ceiving the community norms of alcohol use among students: Some research implications for campus al- cohol education programming. International jour- nal of the Addictions, 21(9-10):961-976.
  18. Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A Smith, and Yejin Choi. 2018. Event2mind: Commonsense inference on events, intents, and reac- tions. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 463-473.
  19. Rezvaneh Rezapour, Saumil H Shah, and Jana Diesner. 2019. Enhancing the measurement of social effects by capturing morality. In Workshop on Computa- tional Approaches to Subjectivity, Sentiment and So- cial Media Analysis, pages 35-45, Stroudsburg, PA, USA. Association for Computational Linguistics.
  20. Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Juraf- sky, Noah A Smith, and Yejin Choi. 2020. Social bias frames: Reasoning about social and power im- plications of language. In ACL.
  21. Maarten Sap, Ronan LeBras, Emily Allaway, Chan- dra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A Smith, and Yejin Choi. 2019. ATOMIC: An atlas of machine commonsense for if- then reasoning. In AAAI.
  22. Richard A Shweder. 1990. In defense of moral re- alism: Reply to gabennesch. Child Development, 61(6):2060-2067.
  23. Yi Tay, Donovan Ong, Jie Fu, Alvin Chan, Nancy Chen, Anh Tuan Luu, and Christopher Pal. 2020. Would you rather? a new benchmark for learning machine alignment with cultural values and social preferences. In Proceedings of the 58th Annual Meeting of the Association for Computational Lin- guistics, pages 5369-5373.
  24. Kristina Toutanova, Dan Klein, Christopher D Man- ning, and Yoram Singer. 2003. Feature-rich part-of- speech tagging with a cyclic dependency network. In Proceedings of the 2003 conference of the North American chapter of the association for computa- tional linguistics on human language technology- volume 1, pages 173-180. Association for Compu- tational Linguistics.
  25. Cynthia Van Hee, Els Lefever, Ben Verhoeven, Julie Mennes, Bart Desmet, Guy De Pauw, Walter Daele- mans, and Veronique Hoste. 2015. Detection and fine-grained classification of cyberbullying events. In Proceedings of the International Conference Re- cent Advances in Natural Language Processing, pages 672-680, Hissar, Bulgaria. INCOMA Ltd. Shoumen, BULGARIA.
  26. Svitlana Volkova, Kyle Shaffer, Jin Yea Jang, and Nathan Hodas. 2017. Separating facts from fic- tion: Linguistic models to classify suspicious and trusted news posts on twitter. In ACL, pages 647- 653, Stroudsburg, PA, USA. Association for Com- putational Linguistics.
  27. Hoa Trong Vu, Graham Neubig, Sakriani Sakti, Tomoki Toda, and Satoshi Nakamura. 2014. Acquir- ing a dictionary of emotion-provoking events. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Lin- guistics, volume 2: Short Papers, pages 128-132.
  28. Su Wang, Greg Durrett, and Katrin Erk. 2018. Model- ing semantic plausibility by injecting world knowl- edge. In NAACL-HLT.
  29. René Weber, J Michael Mangus, Richard Huskey, Fred- eric R Hopp, Ori Amir, Reid Swanson, Andrew Gor- don, Peter Khooshabeh, Lindsay Hahn, and Ron Tamborini. 2018. Extracting latent moral informa- tion from text narratives: Relevance, challenges, and solutions. Commun. Methods Meas., 12(2-3):119- 139.
  30. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier- ric Cistac, Tim Rault, R'emi Louf, Morgan Funtow- icz, and Jamie Brew. 2019. Huggingface's trans- formers: State-of-the-art natural language process- ing. ArXiv, abs/1910.03771. · arXiv
  31. Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending against neural fake news. In NeurIPS.
  32. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Eval- uating text generation with bert. In International Conference on Learning Representations.

Cited by

Sorted by citations

Authors
Forbes, M., Hwang, J. D., Shwartz, V., Sap, M., & Choi, Y.
Affiliations
  • University of Washington (US)
  • Allen Institute for Artificial Intelligence (US)
ORCID
Venue
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Publisher
Association for Computational Linguistics
Published
2020
Pages
653-670
DOI
10.18653/v1/2020.emnlp-main.48
OpenAlex
W3099072156
Cited by
169
References
5
Citations by year
2026: 13 · 2025: 23 · 2024: 28 · 2023: 53 · 2022: 32 · 2021: 18 · 2020: 2
FWCI
34.09
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
  • TIB Data Manager
Funders
  • National Science Foundation (1256082, 1714566)
  • Allen Institute for Artificial Intelligence
  • Defense Advanced Research Projects Agency (N66001, N66001-19-2-4031, N66001-19)
  • Army Research Office (W911NF-15)
  • Naval Information Warfare Center Pacific
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Psychology of Moral and Emotional Judgment
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
Keywords
social norms, moral judgment, rules of thumb, moral foundations, cultural pressure, legality, commonsense reasoning

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