|Contextualizing hate speech classifiers with post-hoc explanation|
B Kennedy, X Jin, AM Davani, M Dehghani, X Ren
Association for Computational Linguistics (ACL), 2020
|Moral foundations twitter corpus: A collection of 35k tweets annotated for moral sentiment|
J Hoover, G Portillo-Wightman, L Yeh, S Havaldar, AM Davani, Y Lin, ...
Social Psychological and Personality Science 11 (8), 1057-1071, 2020
|Dealing with disagreements: Looking beyond the majority vote in subjective annotations|
AM Davani, M Díaz, V Prabhakaran
Transactions of the Association for Computational Linguistics, 2021
|Introducing the Gab Hate Corpus: defining and applying hate-based rhetoric to social media posts at scale|
B Kennedy, M Atari, AM Davani, L Yeh, A Omrani, Y Kim, K Coombs, ...
Language Resources and Evaluation, 1-30, 2022
|On releasing annotator-level labels and information in datasets|
V Prabhakaran, AM Davani, M Diaz
Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd …, 2021
|On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning|
X Jin, F Barbieri, B Kennedy, AM Davani, L Neves, X Ren
Proceedings of the 2021 Conference of the North American Chapter of the …, 2020
|Investigating the role of group-based morality in extreme behavioral expressions of prejudice|
J Hoover, M Atari, A Mostafazadeh Davani, B Kennedy, ...
Nature Communications 12 (1), 4585, 2021
|Towards interacting with smarter systems|
A Mostafazadeh Davani, AA Nazari Shirehjini, S Daraei
Journal of Ambient Intelligence and Humanized Computing 9, 187-209, 2018
|Moral concerns are differentially observable in language|
B Kennedy, M Atari, AM Davani, J Hoover, A Omrani, J Graham, ...
Cognition 212, 104696, 2021
|Morally homogeneous networks and radicalism|
M Atari, AM Davani, D Kogon, B Kennedy, N Ani Saxena, I Anderson, ...
Social Psychological and Personality Science 13 (6), 999-1009, 2022
|A typology and coding manual for the study of hate-based rhetoric|
B Kennedy, D Kogon, K Coombs, J Hoover, C Park, G Portillo-Wightman, ...
PsyArXiv. July 18, 2018
|Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes|
AM Davani, L Yeh, M Atari, B Kennedy, G Portillo-Wightman, E Gonzalez, ...
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019
|Body maps of moral concerns|
M Atari, A Mostafazadeh Davani, M Dehghani
Psychological science 31 (2), 160-169, 2020
|Hate speech classifiers learn human-like social stereotypes|
AM Davani, M Atari, B Kennedy, M Dehghani
arXiv preprint arXiv:2110.14839, 2021
|Improving Counterfactual Generation for Fair Hate Speech Detection|
A Mostafazadeh Davani, A Omrani, B Kennedy, M Atari, X Ren, ...
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), 2021
|A meta user interface for understandable and predictable interaction in aal|
A Mostafazadeh, AAN Shirehjini, S Daraei
Human Aspects of IT for the Aged Population. Design for Everyday Life: First …, 2015
|Findings of the WOAH 5 Shared Task on Fine Grained Hateful Memes Detection|
L Mathias, S Nie, A Davani, D Kiela, V Prabhakaran, B Vidgen, Z Waseem
|Hatred is in the Eye of the Annotator: Hate Speech Classifiers Learn Human-Like Social Stereotypes.|
AM Davani, M Atari, B Kennedy, S Havaldar, M Dehghani
|Pathogens are linked to human moral systems across time and space|
M Atari, NK Reimer, J Graham, J Hoover, B Kennedy, AM Davani, ...
Current Research in Ecological and Social Psychology 3, 100060, 2022
|A meta user interface for interaction with mixed reality environments|
A Mostafazadeh, AAN Shirehjini, S Daraei, N Khojasteh, ...
2015 IEEE International Symposium on Haptic, Audio and Visual Environments …, 2015