{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:48:05Z","timestamp":1783439285611,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":110,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Education and Research (BMBF)","award":["16DII134"],"award-info":[{"award-number":["16DII134"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706598.3713998","type":"proceedings-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T04:24:56Z","timestamp":1745468696000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-5287","authenticated-orcid":false,"given":"David","family":"Hartmann","sequence":"first","affiliation":[{"name":"Weizenbaum Institute Berlin, Berlin, Germany and Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6356-2372","authenticated-orcid":false,"given":"Amin","family":"Oueslati","sequence":"additional","affiliation":[{"name":"Hertie School Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1671-222X","authenticated-orcid":false,"given":"Dimitri","family":"Staufer","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9922-4196","authenticated-orcid":false,"given":"Lena","family":"Pohlmann","sequence":"additional","affiliation":[{"name":"Weizenbaum Institute Berlin, Berlin, Germany and Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4760-367X","authenticated-orcid":false,"given":"Simon","family":"Munzert","sequence":"additional","affiliation":[{"name":"Hertie School Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1919-9016","authenticated-orcid":false,"given":"Hendrik","family":"Heuer","sequence":"additional","affiliation":[{"name":"Center for Advanced Internet Studies (CAIS), Bochum, Germany and University of Wuppertal, Wuppertal, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Sana Ahmad. 2023. Ground Control: Organizing Content Moderation for Social Media Platforms. 10.17169\/REFUBIUM-40700","DOI":"10.17169\/REFUBIUM-40700"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Wafa Alorainy Pete Burnap Huan Liu and Matthew\u00a0L. Williams. 2019. \"The Enemy Among Us\": Detecting Cyber Hate Speech with Threats-based Othering Language Embeddings. ACM Transactions on the Web 13 3 (July 2019) 1\u201326. 10.1145\/3324997Retrieved 2020-01-21.","DOI":"10.1145\/3324997"},{"key":"e_1_3_3_3_4_2","volume-title":"The Stanford Encyclopedia of Philosophy (fall 2023 ed.)","author":"Anderson Luvell","year":"2023","unstructured":"Luvell Anderson and Michael Barnes. 2023. Hate Speech. In The Stanford Encyclopedia of Philosophy (fall 2023 ed.), Edward\u00a0N. Zalta and Uri Nodelman (Eds.). Metaphysics Research Lab, Stanford University, Online. https:\/\/plato.stanford.edu\/archives\/fall2023\/entries\/hate-speech\/"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Jack Bandy. 2021. Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits. ACM Transactions on Computer-Human Interaction 5 CSCW1 (April 2021) 1\u201334.","DOI":"10.1145\/3449148"},{"key":"e_1_3_3_3_6_2","volume-title":"Fairness in Machine Learning: Limitations and Opportunities","author":"Barocas Solon","year":"2023","unstructured":"Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2023. Fairness in Machine Learning: Limitations and Opportunities. MIT Press, Cambridge, MA. https:\/\/fairmlbook.org\/"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Niklas Barth Elke Wagner Philipp Raab and Bj\u00f6rn Wieg\u00e4rtner. 2023. Contextures of Hate: Towards a Systems Theory of Hate Communication on Social Media Platforms. The Communication Review 26 3 (2023) 209\u2013252. 10.1080\/10714421.2023.2208513","DOI":"10.1080\/10714421.2023.2208513"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67256-4_32"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00037"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1120"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1176"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Alexander Brown. 2017. What is Hate Speech? Part 2: Family Resemblances. Law and Philosophy 36 5 (Oct. 2017) 561\u2013613. 10.1007\/s10982-017-9300-x","DOI":"10.1007\/s10982-017-9300-x"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650882"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659037"},{"key":"e_1_3_3_3_17_2","volume-title":"Moderate Text | Cloud Natural Language API","author":"Cloud Google","year":"2025","unstructured":"Google Cloud. 2025. Moderate Text | Cloud Natural Language API. Google Cloud. https:\/\/cloud.google.com\/natural-language\/docs\/moderating-text"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20 1 (1960) 37\u201346.","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Aida\u00a0Mostafazadeh Davani Mohammad Atari Brendan Kennedy and Morteza Dehghani. 2023. Hate Speech Classifiers Learn Normative Social Stereotypes. Transactions of the Association for Computational Linguistics 11 (03 2023) 300\u2013319. 10.1162\/tacl_a_00550 arXiv:https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00550\/2075730\/tacl_a_00550.pdf","DOI":"10.1162\/tacl_a_00550"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3504"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"G De\u00a0Gregorio. 2020. Democratising online content moderation: A constitutional framework. Computer Law & Security Review 36 (2020) 105376.","DOI":"10.1016\/j.clsr.2019.105376"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.26092\/ELIB\/2707"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Thiago Dias\u00a0Oliva Dennys\u00a0Marcelo Antonialli and Alessandra Gomes. 2021. Fighting Hate Speech Silencing Drag Queens? Artificial Intelligence in Content Moderation and Risks to LGBTQ Voices Online. Sexuality & Culture 25 2 (2021) 700\u2013732. Issue 2. 10.1007\/s12119-020-09790-w","DOI":"10.1007\/s12119-020-09790-w"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278729"},{"key":"e_1_3_3_3_25_2","unstructured":"Evelyn Douek. 2021. Governing Online Speech: From \u2018Posts-as-Trumps\u2019 to Proportionality and Probability. Columbia Law Review 121 3 (2021) 759\u2013833."},{"key":"e_1_3_3_3_26_2","unstructured":"Fatma Elsafoury Stamos Katsigiannis and Naeem Ramzan. 2023. On Bias and Fairness in NLP: How to have a fairer text classification?http:\/\/arxiv.org\/abs\/2305.12829 arXiv:https:\/\/arXiv.org\/abs\/2305.12829 [cs]."},{"key":"e_1_3_3_3_27_2","first-page":"1263","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Elsafoury Fatma","year":"2022","unstructured":"Fatma Elsafoury, Steve\u00a0R. Wilson, Stamos Katsigiannis, and Naeem Ramzan. 2022. SOS: Systematic Offensive Stereotyping Bias in Word Embeddings. In Proceedings of the 29th International Conference on Computational Linguistics, Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony\u00a0Kyungil Lee, Enrico Santus, Francis Bond, and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 1263\u20131274. https:\/\/aclanthology.org\/2022.coling-1.108"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.29"},{"key":"e_1_3_3_3_29_2","unstructured":"European Commission. 2024. Supervision of the designated very large online platforms and search engines under DSA. https:\/\/digital-strategy.ec.europa.eu\/en\/policies\/list-designated-vlops-and-vloses#ecl-inpage-google Last accessed 2024-04-29."},{"key":"e_1_3_3_3_30_2","unstructured":"European Parliament. 2022. Regulation (EU)2022\/2065 of the European Parliament and of the Council of 19 October 2022 on a Single Market For Digital Services and amending Directive 2000\/31\/EC (Digital Services Act). https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=celex%3A32022R2065 Last accessed 2024-04-29."},{"key":"e_1_3_3_3_31_2","first-page":"6786","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Fortuna Paula","year":"2020","unstructured":"Paula Fortuna, Juan Soler, and Leo Wanner. 2020. Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets. In Proceedings of the Twelfth Language Resources and Evaluation Conference, Nicoletta Calzolari, Fr\u00e9d\u00e9ric B\u00e9chet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association, Marseille, France, 6786\u20136794. https:\/\/aclanthology.org\/2020.lrec-1.838"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1534-0856(02)05009-0"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Isabel\u00a0O. Gallegos Ryan\u00a0A. Rossi Joe Barrow Md\u00a0Mehrab Tanjim Sungchul Kim Franck Dernoncourt Tong Yu Ruiyi Zhang and Nesreen\u00a0K. Ahmed. 2024. Bias and Fairness in Large Language Models: A Survey. Computational Linguistics 50 3 (09 2024) 1097\u20131179. 10.1162\/coli_a_00524 arXiv:https:\/\/direct.mit.edu\/coli\/article-pdf\/50\/3\/1097\/2471010\/coli_a_00524.pdf","DOI":"10.1162\/coli_a_00524"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Tanmay Garg Sarah Masud Tharun Suresh and Tanmoy Chakraborty. 2023. Handling bias in toxic speech detection: A survey. Comput. Surveys 55 13s (2023) 1\u201332.","DOI":"10.1145\/3580494"},{"key":"e_1_3_3_3_35_2","volume-title":"Content moderation: The harrowing, traumatizing job that left many African data workers with mental health issues and drug dependency","author":"Gebrekidan Fasica\u00a0B.","year":"2024","unstructured":"Fasica\u00a0B. Gebrekidan. 2024. Content moderation: The harrowing, traumatizing job that left many African data workers with mental health issues and drug dependency. DAIR Institute. https:\/\/data-workers.org\/fasica"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.35"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","unstructured":"Tarleton Gillespie. 2022. Do Not Recommend? Reduction as a Form of Content Moderation. Social Media + Society 8 3 (2022) 20563051221117552. 10.1177\/20563051221117552 arXiv:10.1177\/20563051221117552","DOI":"10.1177\/20563051221117552"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Robert Gorwa Reuben Binns and Christian Katzenbach. 2020. Algorithmic content moderation: Technical and political challenges in the automation of platform governance. Big Data & Society 7 1 (Jan. 2020) 205395171989794. 10.1177\/2053951719897945","DOI":"10.1177\/2053951719897945"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157469"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-024-00595-3"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641949"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Manoel Horta\u00a0Ribeiro. 2024. Content Moderation in Online Platforms. 10.5075\/EPFL-THESIS-10387","DOI":"10.5075\/EPFL-THESIS-10387"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.2307\/jj.11895528.7"},{"key":"e_1_3_3_3_45_2","unstructured":"Jigsaw. 2019. Jigsaw toxic comment classifi- cation challenge.https:\/\/www.kaggle.com\/c\/jigsaw-toxic-comment-classification-challenge"},{"key":"e_1_3_3_3_46_2","unstructured":"Jigsaw. 2021. Google\u2019s Jigsaw Announces Toxicity-Reducing API Perspective is Processing 500M Requests Daily. https:\/\/www.prnewswire.com\/news-releases\/googles-jigsaw-announces-toxicity-reducing-api-perspective-is-processing-500m-requests-daily-301223600.html"},{"key":"e_1_3_3_3_47_2","volume-title":"Algorithmic Accountability: Moving Beyond Audits","author":"Kak Amba","year":"2023","unstructured":"Amba Kak and Sarah\u00a0Myers West. 2023. Algorithmic Accountability: Moving Beyond Audits. AI Now Institute. https:\/\/ainowinstitute.org\/publication\/algorithmic-accountability"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","unstructured":"Sayash Kapoor and Arvind Narayanan. 2023. Leakage and the reproducibility crisis in machine-learning-based science. Article Volume 4 Issue 9 4 9 (September 08 2023) 100804. 10.1016\/j.mlops.2023.100804Open access.","DOI":"10.1016\/j.mlops.2023.100804"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Ramzi Khezzar Abdelrahman Moursi and Zaher Al\u00a0Aghbari. 2023. arHateDetector: detection of hate speech from standard and dialectal Arabic Tweets. Discover Internet of Things 3 1 (March 2023) 1.","DOI":"10.1007\/s43926-023-00030-9"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3640736"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Bo Li Peng Qi Bo Liu Shuai Di Jingen Liu Jiquan Pei Jinfeng Yi and Bowen Zhou. 2023. Trustworthy AI: From principles to practices. Comput. Surveys 55 9 (2023) 1\u201346.","DOI":"10.1145\/3555803"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.woah-1.4"},{"key":"e_1_3_3_3_53_2","volume-title":"An Introduction to Explainable AI with Shapley Values \u2014 SHAP Latest Documentation","author":"Lundberg Scott","year":"2018","unstructured":"Scott Lundberg. 2018. An Introduction to Explainable AI with Shapley Values \u2014 SHAP Latest Documentation. Scott Lundberg. https:\/\/shap.readthedocs.io\/en\/latest\/example_notebooks\/overviews\/An%20introduction%20to%20explainable%20AI%20with%20Shapley%20values.html"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_3_3_3_55_2","unstructured":"Thodoris Lykouris and Wentao Weng. 2024. Learning to Defer in Content Moderation: The Human-AI Interplay. arxiv:https:\/\/arXiv.org\/abs\/2402.12237\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2402.12237"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Qing Lyu Marianna Apidianaki and Chris Callison-Burch. 2024. Towards Faithful Model Explanation in NLP: A Survey. Computational Linguistics 50 2 (06 2024) 657\u2013723. 10.1162\/coli_a_00511 arXiv:https:\/\/direct.mit.edu\/coli\/article-pdf\/50\/2\/657\/2457495\/coli_a_00511.pdf","DOI":"10.1162\/coli_a_00511"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Renkai Ma Yue You Xinning Gui and Yubo Kou. 2023. How Do Users Experience Moderation?: A Systematic Literature Review. Proc. ACM Hum.-Comput. Interact. 7 CSCW2 Article 278 (oct 2023) 30\u00a0pages. 10.1145\/3610069","DOI":"10.1145\/3610069"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658932"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","unstructured":"Teresa Marques. 2023. The Expression of Hate in Hate Speech. Journal of Applied Philosophy 40 5 (2023) 769\u2013787. 10.1111\/japp.12608 arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/japp.12608","DOI":"10.1111\/japp.12608"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"crossref","unstructured":"Binny Mathew Punyajoy Saha Seid\u00a0Muhie Yimam Chris Biemann Pawan Goyal and Animesh Mukherjee. 2021. HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection. Proceedings of the AAAI Conference on Artificial Intelligence 35 17 (May 2021) 14867\u201314875. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17745 Number: 17.","DOI":"10.1609\/aaai.v35i17.17745"},{"key":"e_1_3_3_3_61_2","volume-title":"Words That Wound: Critical Race Theory, Assaultive Speech, and The First Amendment","author":"Matsuda Mari\u00a0J.","year":"1993","unstructured":"Mari\u00a0J. Matsuda, Charles R.\u00a0Lawrence III, Richard Delgado, and Kimberl\u00e9\u00a0W. Crenshaw. 1993. Words That Wound: Critical Race Theory, Assaultive Speech, and The First Amendment. Faculty Books, New York. https:\/\/scholarship.law.columbia.edu\/books\/287 Accessed: date-of-access."},{"key":"e_1_3_3_3_62_2","first-page":"1","volume-title":"Who Trains the Data for European Artificial Intelligence?: Report of the European Microworkers Communication and Outreach Initiative (EnCOre, 2023-2024)","author":"Miceli Milagros","year":"2024","unstructured":"Milagros Miceli, Paola Tubaro, Antonio\u00a0A. Casilli, Thomas Le\u00a0Bonniec, and Camilla\u00a0Salim Wagner. 2024. Who Trains the Data for European Artificial Intelligence?: Report of the European Microworkers Communication and Outreach Initiative (EnCOre, 2023-2024). Technical Report. European Parliament; The Left. 1\u201340 pages."},{"key":"e_1_3_3_3_63_2","first-page":"1","volume-title":"Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis","author":"Mihaljevi\u0107 Helena","year":"2022","unstructured":"Helena Mihaljevi\u0107 and Elisabeth Steffen. 2022. How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content. In Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis (2022-09-12). CPSS-2022, Hochschule f\u00fcr Technik und Wirtschaft Berlin, Potsdam, Germany, 1\u201312."},{"key":"e_1_3_3_3_64_2","unstructured":"Pushkar Mishra Helen Yannakoudakis and Ekaterina Shutova. 2019. Tackling Online Abuse: A Survey of Automated Abuse Detection Methods. http:\/\/arxiv.org\/abs\/1908.06024 Retrieved 2020-02-04."},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_3_3_66_2","unstructured":"Christoph Molnar. 2022. Interpretable Machine Learning. https:\/\/christophm.github.io\/interpretable-ml-book"},{"key":"e_1_3_3_3_67_2","first-page":"4593","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Mosca Edoardo","year":"2022","unstructured":"Edoardo Mosca, Ferenc Szigeti, Stella Tragianni, Daniel Gallagher, and Georg Groh. 2022. SHAP-Based Explanation Methods: A Review for NLP Interpretability. In Proceedings of the 29th International Conference on Computational Linguistics, Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony\u00a0Kyungil Lee, Enrico Santus, Francis Bond, and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 4593\u20134603. https:\/\/aclanthology.org\/2022.coling-1.406"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.socialnlp-1.8"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"crossref","unstructured":"Marzieh Mozafari Reza Farahbakhsh and No\u00ebl Crespi. 2020. Hate speech detection and racial bias mitigation in social media based on BERT model. PloS one 15 8 (2020) e0237861.","DOI":"10.1371\/journal.pone.0237861"},{"key":"e_1_3_3_3_70_2","volume-title":"Introduction to machine learning with Python: a guide for data scientists","author":"M\u00fcller Andreas\u00a0C","year":"2016","unstructured":"Andreas\u00a0C M\u00fcller and Sarah Guido. 2016. Introduction to machine learning with Python: a guide for data scientists. \" O\u2019Reilly Media, Inc.\", Delaware, USA."},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642025"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","unstructured":"Kevin Munger. 2019. The Limited Value of Non-Replicable Field Experiments in Contexts With Low Temporal Validity. Social Media + Society 5 3 (2019) 2056305119859294. 10.1177\/2056305119859294 arXiv:10.1177\/2056305119859294","DOI":"10.1177\/2056305119859294"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"W.\u00a0James Murdoch Chandan Singh Karl Kumbier Reza Abbasi-Asl and Bin Yu. 2019. Definitions methods and applications in interpretable machine learning. Proceedings of the National Academy of Sciences 116 44 (2019) 22071\u201322080. 10.1073\/pnas.1900654116 arXiv:https:\/\/www.pnas.org\/doi\/pdf\/10.1073\/pnas.1900654116","DOI":"10.1073\/pnas.1900654116"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Shubhanshu Nagar Faysal\u00a0A. Barbhuiya and Koushik Dey. 2023. Towards more robust hate speech detection: using social context and user data. Social Network Analysis and Mining 13 47 (2023) 1\u201314. 10.1007\/s13278-023-01051-6","DOI":"10.1007\/s13278-023-01051-6"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.trustnlp-1.3"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v19i1.35876"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3350546.3352512"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","unstructured":"Marie Ozanne Ameya Bhandari Natalya\u00a0N. Bazarova and Dominic DiFranzo. 2022. Shall AI Moderators Be Made Visible? Perception of Accountability and Trust in Moderation Systems on Social Media Platforms. Big Data & Society 9 2 (2022) 1\u201313. 10.1177\/20539517221115666","DOI":"10.1177\/20539517221115666"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1302"},{"key":"e_1_3_3_3_80_2","volume-title":"Overreliance on AI: Literature Review","author":"Passi Samir","year":"2022","unstructured":"Samir Passi and Mihaela Vorvoreanu. 2022. Overreliance on AI: Literature Review. Technical Report MSR-TR-2022-12. Microsoft. https:\/\/www.microsoft.com\/en-us\/research\/publication\/overreliance-on-ai-literature-review\/"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1578"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1578"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","unstructured":"Juan\u00a0Manuel P\u00e9rez Franco\u00a0M. Luque Demian Zayat Mart\u00edn Kondratzky Agust\u00edn Moro Pablo\u00a0Santiago Serrati Joaqu\u00edn Zajac Paula Miguel Natalia Debandi Agust\u00edn Gravano and Viviana Cotik. 2023. Assessing the Impact of Contextual Information in Hate Speech Detection. IEEE Access 11 (2023) 30575\u201330590. 10.1109\/ACCESS.2023.3258973","DOI":"10.1109\/ACCESS.2023.3258973"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314244"},{"key":"e_1_3_3_3_85_2","unstructured":"Inioluwa\u00a0Deborah Raji Peggy Xu Colleen Honigsberg and Daniel\u00a0E. Ho. 2022. Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance. http:\/\/arxiv.org\/abs\/2206.04737 arXiv:https:\/\/arXiv.org\/abs\/2206.04737 [cs]."},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","unstructured":"Bernhard Rieder and Yarden Skop. 2021. The fabrics of machine moderation: Studying the technical normative and organizational structure of Perspective API. Big Data & Society 8 2 (2021) 20539517211046181. 10.1177\/20539517211046181 arXiv:10.1177\/20539517211046181","DOI":"10.1177\/20539517211046181"},{"key":"e_1_3_3_3_87_2","volume-title":"ChatGPT\u2019s weekly users have doubled in less than a year","author":"Roth Emma","year":"2024","unstructured":"Emma Roth. 2024. ChatGPT\u2019s weekly users have doubled in less than a year. The Verge. https:\/\/www.theverge.com Accessed: 2024-12-10."},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.4"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/778"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1163"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.486"},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.431"},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.431"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642333"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581020"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581538"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1339"},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501879"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.132"},{"key":"e_1_3_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3012"},{"key":"e_1_3_3_3_101_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2013"},{"key":"e_1_3_3_3_102_2","first-page":"576","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Wiegand Michael","year":"2021","unstructured":"Michael Wiegand, Josef Ruppenhofer, and Elisabeth Eder. 2021. Implicitly Abusive Language \u2013 What does it actually look like and why are we not getting there?. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz\u00a0Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou (Eds.). Association for Computational Linguistics, Online, 576\u2013587. https:\/\/aclanthology.org\/2021.naacl-main.48"},{"key":"e_1_3_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1060"},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.socialnlp-1.2"},{"key":"e_1_3_3_3_105_2","series-title":"Proceedings of Machine Learning Research","first-page":"24929","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Yan Tom","year":"2022","unstructured":"Tom Yan and Chicheng Zhang. 2022. Active fairness auditing. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, Baltimore, Maryland, USA, 24929\u201324962. https:\/\/proceedings.mlr.press\/v162\/yan22c.html"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"publisher","unstructured":"Wenqi Yin and Arkaitz Zubiaga. 2021. Towards generalisable hate speech detection: a review on obstacles and solutions. PeerJ Computer Science 7 (2021) e598. 10.7717\/peerj-cs.598","DOI":"10.7717\/peerj-cs.598"},{"key":"e_1_3_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.conll-1.3"},{"key":"e_1_3_3_3_108_2","unstructured":"Xinchen Yu Eduardo Blanco and Lingzi Hong. 2022. Hate Speech and Counter Speech Detection: Conversational Context Does Matter. arxiv:https:\/\/arXiv.org\/abs\/2206.06423\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2206.06423"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.300"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.274"},{"key":"e_1_3_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1145\/3614419.3644025"}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713998","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3713998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:14:23Z","timestamp":1751606063000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":110,"alternative-id":["10.1145\/3706598.3713998","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3713998","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}