CoChat
Sign Up
Cited by 49Ethics and Social Impacts of AIComputational and Text Analysis MethodsQualitative Research Methods and Ethics

Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science

Open access
Cambo, Scott Allen, Gergle, Darren·2022·CHI Conference on Human Factors in Computing Systems
DOI 10.1145/3491102.3501998
Open this paper in CoChat — free accountOpen PDF

Abstract

Data science and machine learning provide indispensable techniques for understanding phenomena at scale, but the discretionary choices made when doing this work are often not recognized. Drawing from qualitative research practices, we describe how the concepts of positionality and reflexivity can be adapted to provide a framework for understanding, discussing, and disclosing the discretionary choices and subjectivity inherent to data science work. We first introduce the concepts of model positionality and computational reflexivity that can help data scientists to reflect on and communicate the social and cultural context of a model’s development and use, the data annotators and their annotations, and the data scientists themselves. We then describe the unique challenges of adapting these concepts for data science work and offer annotator fingerprinting and position mining as promising solutions. Finally, we demonstrate these techniques in a case study of the development of classifiers for toxic commenting in online communities.

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 · 10.1145/3491102.3501998

Cites

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?

Self-check

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

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

The citation lists haven’t been fetched yet

References 65 · Cited by 49

Research works printed but not linked: 64

  1. Sweta Agrawal and Amit Awekar. 2018. Deep Learning for Detecting Cyber- bullying Across Multiple Social Media Platforms. In Advances in Information Retrieval (2018) (Lecture Notes in Computer Science), Gabriella Pasi, Benjamin Piwowarski, Leif Azzopardi, and Allan Hanbury (Eds.). Springer International Publishing, 141-153.
  2. M. A. Al-Ajlan and M. Ykhlef. 2018. Optimized Twitter Cyberbullying Detection based on Deep Learning. In 2018 21st Saudi Computer Society National Computer Conference (NCC) (2018-04). 1-5. https://doi.org/10.1109/NCG.2018.8593146 · DOI
  3. Cecilia Aragon, Clayton Hutto, Andy Echenique, Brittany Fiore-Gartland, Yun Huang, Jinyoung Kim, Gina Nef, Wanli Xing, and Joseph Bayer. 2016. Developing a Research Agenda for Human-Centered Data Science. In Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion -CSCW '16 Companion (San Francisco, California, USA, 2016). ACM Press, 529-535. https://doi.org/10.1145/2818052.2855518 · DOI
  4. Lora Aroyo, Lucas Dixon, Nithum Thain, Olivia Redfeld, and Rachel Rosen. 2019. Crowdsourcing Subjective Tasks: The Case Study of Understanding Toxicity in Online Discussions. In Companion Proceedings of The 2019 World Wide Web Conference (New York, NY, USA, 2019) (WWW '19). ACM, 1100-1105. https: //doi.org/10.1145/3308560.3317083 · DOI
  5. Lora Aroyo and Chris Welty. 2014. The Three Sides of CrowdTruth. 1, 1 (2014). https://doi.org/10.15346/hc.v1i1.3 · DOI · Paper page
  6. Lora Aroyo and Chris Welty. 2015. Truth Is a Lie: Crowd Truth and the Seven Myths of Human Annotation. 36, 1 (2015), 15-24. https://doi.org/10.1609/aimag. v36i1.2564 · DOI
  7. Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, and Vasudeva Varma. 2017. Deep Learning for Hate Speech Detection in Tweets. In Proceedings of the 26th International Conference on World Wide Web Companion (Republic and Canton of Geneva, Switzerland, 2017) (WWW '17 Companion). International World Wide Web Conferences Steering Committee, 759-760. https://doi.org/10.1145/3041021. 3054223 · DOI
  8. Jo Bates, David Cameron, Alessandro Checco, Paul Clough, Frank Hopfgartner, Suvodeep Mazumdar, Laura Sbaf, Peter Stordy, and Antonio de la Vega de León. 2020. Integrating FATE/critical data studies into data science curricula: where are we going and how do we get there?. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (New York, NY, USA, 2020-01-27) (FAT* '20). Association for Computing Machinery, 425-435. https://doi.org/10. 1145/3351095.3372832 · DOI
  9. Eric PS Baumer, David Mimno, Shion Guha, Emily Quan, and Geri K Gay. 2017. Comparing grounded theory and topic modeling: Extreme divergence or unlikely convergence? Journal of the Association for Information Science and Technology 68, 6 (2017), 1397-1410.
  10. Reuben Binns, Michael Veale, Max Van Kleek, and Nigel Shadbolt. 2017. Like trainer, like bot? Inheritance of bias in algorithmic content moderation. 10540 (2017), 405-415. https://doi.org/10.1007/978-3-319-67256-4_32 arXiv:1707.01477 · DOI
  11. Victoria Bobicev and Marina Sokolova. 2017. Inter-Annotator Agreement in Sentiment Analysis: Machine Learning Perspective. In RANLP 2017 -Recent Advances in Natural Language Processing Meet Deep Learning (2017-11-10). Incoma Ltd. Shoumen, Bulgaria, 97-102. https://doi.org/10.26615/978-954-452-049-6_ 015 · DOI
  12. Peter Bourgonje, Julian Moreno-Schneider, Ankit Srivastava, and Georg Rehm. 2018. Automatic Classifcation of Abusive Language and Personal Attacks in Various Forms of Online Communication. In Language Technologies for the Chal- lenges of the Digital Age (2018) (Lecture Notes in Computer Science), Georg Rehm and Thierry Declerck (Eds.). Springer International Publishing, 180-191.
  13. danah boyd and Kate Crawford. 2012. CRITICAL QUESTIONS FOR BIG DATA: Provocations for a cultural, technological, and scholarly phenomenon. Informa- tion, Communication & Society 15, 5 (June 2012), 662-679. https://doi.org/10. 1080/1369118X.2012.678878 · DOI · Paper page
  14. Scott Allen Cambo. 2020. Model Positionality: A Novel Framework for Data Science with Subjective Target Concepts. Ph.D. Dissertation. Northwestern University, ProQuest Dissertations Publishing.
  15. Scott Allen Cambo and Darren Gergle. 2018. User-Centred Evaluation for Machine Learning. In Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, Jianlong Zhou and Fang Chen (Eds.). Springer International Publishing, 315-339. https://doi.org/10.1007/978-3-319-90403-0_16 · DOI
  16. Justin Cheng, Cristian Danescu-Niculescu-Mizil, and Jure Leskovec. 2015. An- tisocial Behavior in Online Discussion Communities. (2015). arXiv:1504.00680 http://arxiv.org/abs/1504.00680 · arXiv
  17. David Coghlan and Mary Brydon-Miller. 2014. Positionality. SAGE Publications Ltd. https://doi.org/10.4135/9781446294406.n277 · DOI
  18. Jacob Cohen. 1968. Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. 70, 4 (1968), 213-220. https://doi.org/10. 1037/h0026256 · DOI · Paper page
  19. Jacob Cohen. 1988. Statistical power analysis for the behavioral sciences (2nd ed ed.). L. Erlbaum Associates.
  20. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. Automated Hate Speech Detection and the Problem of Ofensive Language. (2017). arXiv:1703.04009 http://arxiv.org/abs/1703.04009 · arXiv
  21. Catherine D'Ignazio and Lauren F. Klein. 2020. Data feminism. The MIT Press, Cambridge, Massachusetts.
  22. Karthik Dinakar, Roi Reichart, and Henry Lieberman. 2011. Modeling the Detec- tion of Textual Cyberbullying. In Fifth International AAAI Conference on Weblogs and Social Media (2011-07-06). https://www.aaai.org/ocs/index.php/ICWSM/ ICWSM11/paper/view/3841
  23. Pierre Dragicevic, Yvonne Jansen, Abhraneel Sarma, Matthew Kay, and Fanny Chevalier. 2019. Increasing the Transparency of Research Papers with Explorable Multiverse Analyses. Association for Computing Machinery, New York, NY, USA, 1-15. https://doi.org/10.1145/3290605.3300295 · DOI
  24. Anca Dumitrache, Lora Aroyo, and Chris Welty. 2018. Crowdsourcing Semantic Label Propagation in Relation Classifcation. (2018). arXiv:1809.00537 http: //arxiv.org/abs/1809.00537 · arXiv
  25. Anca Dumitrache, Oana Inel, Lora Aroyo, Benjamin Timmermans, and Chris Welty. 2018. CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagree- ment. (2018). arXiv:1808.06080 http://arxiv.org/abs/1808.06080 · arXiv
  26. M. C. Elish and danah boyd. 2018. Situating methods in the magic of Big Data and AI. Communication Monographs 85, 1 (Jan. 2018), 57-80. https://doi.org/10. 1080/03637751.2017.1375130 · DOI
  27. Mai ElSherief, Shirin Nilizadeh, Dana Nguyen, Giovanni Vigna, and Elizabeth Belding. 2018. Peer to Peer Hate: Hate Speech Instigators and Their Targets. In Twelfth International AAAI Conference on Web and Social Media. https://www. aaai.org/ocs/index.php/ICWSM/ICWSM18/paper/view/17905
  28. Ethan Fast, Binbin Chen, and Michael Bernstein. 2016. Empath: Understanding Topic Signals in Large-Scale Text. (2016), 4647-4657. https://doi.org/10.1145/ 2858036.2858535 arXiv:1602.06979 · DOI · Paper page
  29. Rebecca Fiebrink and Marco Gillies. 2018. Introduction to the Special Issue on Human-Centered Machine Learning. 8, 2 (2018), 7:1-7:7. https://doi.org/10.1145/ 3205942 · DOI
  30. Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. 2020. Datasheets for Datasets. (2020). arXiv:1803.09010 http://arxiv.org/abs/1803.09010 · arXiv
  31. Marco Gillies, Rebecca Fiebrink, Atau Tanaka, Jérémie Garcia, Frédéric Bevilac- qua, Alexis Heloir, Fabrizio Nunnari, Wendy Mackay, Saleema Amershi, Bongshin Lee, Nicolas d'Alessandro, Joëlle Tilmanne, Todd Kulesza, and Baptiste Carami- aux. 2016. Human-Centred Machine Learning. In Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems (San Jose, California, USA, 2016-05-07) (CHI EA '16). Association for Computing Machinery, 3558-3565. https://doi.org/10.1145/2851581.2856492 · DOI
  32. B. Green. 2019. "Good" isn't good enough. In Proceedings of the AI for Social Good workshop at NeurIPS (2019).
  33. Carlos Guestrin. 2019. 4 Systems Perspectives into Human-Centered Machine Learning. In The 25th Annual International Conference on Mobile Computing and Networking (Los Cabos, Mexico, 2019-10-11) (MobiCom '19). Association for Computing Machinery, 1-2. https://doi.org/10.1145/3300061.3356017 · DOI
  34. Christoph Hube, Besnik Fetahu, and Ujwal Gadiraju. 2019. Understanding and Mitigating Worker Biases in the Crowdsourced Collection of Subjective Judgments. Association for Computing Machinery, New York, NY, USA, 1-12. https://doi. org/10.1145/3290605.3300637 · DOI · Paper page
  35. Andrew Iliadis and Federica Russo. 2016. Critical data studies: An introduction. Big Data & Society 3, 2 (Dec. 2016), 205395171667423. https://doi.org/10.1177/ 2053951716674238 · DOI
  36. Oana Inel, Khalid Khamkham, Tatiana Cristea, Anca Dumitrache, Arne Rut- jes, Jelle van der Ploeg, Lukasz Romaszko, Lora Aroyo, and Robert-Jan Sips. 2014. CrowdTruth: Machine-Human Computation Framework for Harnessing Disagreement in Gathering Annotated Data. In The Semantic Web -ISWC 2014, Peter Mika, Tania Tudorache, Abraham Bernstein, Chris Welty, Craig Knoblock, Denny Vrandečić, Paul Groth, Natasha Noy, Krzysztof Janowicz, and Carole Goble (Eds.). Vol. 8797. Springer International Publishing, 486-504. https://doi.org/10.1007/978-3-319-11915-1_31 · DOI · Paper page
  37. Marina Kogan, Aaron Halfaker, Shion Guha, Cecilia Aragon, Michael Muller, and Stuart Geiger. 2020. Mapping Out Human-Centered Data Science: Methods, Approaches, and Best Practices. In Companion of the 2020 ACM International Conference on Supporting Group Work (Sanibel Island, Florida, USA) (GROUP '20). Association for Computing Machinery, New York, NY, USA, 151-156. https: //doi.org/10.1145/3323994.3369898 · DOI
  38. Scott M Lundberg and Su-In Lee. [n.d.]. A Unifed Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30, I.
  39. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc., 4765-4774. http://papers.nips.cc/paper/7062-a- unifed-approach-to-interpreting-model-predictions.pdf
  40. Leland McInnes, John Healy, and James Melville. 2018. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. (2018). arXiv:1802.03426 http://arxiv.org/abs/1802.03426 · arXiv
  41. Milagros Miceli, Tianling Yang, Laurens Naudts, Martin Schuessler, Diana Ser- banescu, and Alex Hanna. 2021. Documenting Computer Vision Datasets: An Invitation to Refexive Data Practices. In Proceedings of the 2021 ACM Con- ference on Fairness, Accountability, and Transparency (Virtual Event, Canada) (FAccT '21). Association for Computing Machinery, New York, NY, USA, 161-172. https://doi.org/10.1145/3442188.3445880 · DOI
  42. Michael Muller, Cecilia Aragon, Shion Guha, Marina Kogan, Gina Nef, Cathrine Seidelin, Katie Shilton, and Anissa Tanweer. 2020. Interrogating Data Science. Association for Computing Machinery, New York, NY, USA, 467-473. https: //doi.org/10.1145/3406865.3418584 · DOI
  43. Michael Muller, Melanie Feinberg, Timothy George, Steven J. Jackson, Bon- nie E. John, Mary Beth Kery, and Samir Passi. 2019. Human-Centered Study of Data Science Work Practices. In Extended Abstracts of the 2019 CHI Con- ference on Human Factors in Computing Systems (Glasgow, Scotland Uk) (CHI EA '19). Association for Computing Machinery, New York, NY, USA, 1-8. https://doi.org/10.1145/3290607.3299018 · DOI
  44. Michael Muller, Shion Guha, Eric P.S. Baumer, David Mimno, and N. Sadat Shami. 2016. Machine Learning and Grounded Theory Method: Convergence, Diver- gence, and Combination. In Proceedings of the 19th International Conference on Sup- porting Group Work (Sanibel Island, Florida, USA, 2016-11-13) (GROUP '16). Asso- ciation for Computing Machinery, 3-8. https://doi.org/10.1145/2957276.2957280 · DOI
  45. Chikashi Nobata, Joel Tetreault, Achint Thomas, Yashar Mehdad, and Yi Chang. 2016. Abusive Language Detection in Online User Content. In Proceedings of the 25th International Conference on World Wide Web (Republic and Canton of Geneva, Switzerland, 2016) (WWW '16). International World Wide Web Conferences Steering Committee, 145-153. https://doi.org/10.1145/2872427.2883062 · DOI
  46. Brendan O'Connor, David Bamman, and Noah A Smith. 2011. Computational text analysis for social science: Model complexity and assumptions. In Proc. of the NIPS Workshop on Comptuational Social Science and the Wisdom of Crowds.
  47. Samir Passi and Steven Jackson. 2017. Data Vision: Learning to See Through Algorithmic Abstraction. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing (New York, NY, USA, 2017) (CSCW '17). ACM, 2436-2447. https://doi.org/10.1145/2998181.2998331 · DOI
  48. John Pavlopoulos, Prodromos Malakasiotis, and Ion Androutsopoulos. 2017. Deep Learning for User Comment Moderation. (2017). arXiv:1705.09993 http://arxiv. org/abs/1705.09993 · arXiv
  49. John Pavlopoulos, Prodromos Malakasiotis, and Ion Androutsopoulos. 2017. Deeper Attention to Abusive User Content Moderation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (Copen- hagen, Denmark, 2017). Association for Computational Linguistics, 1125-1135. https://doi.org/10.18653/v1/D17-1117 · DOI
  50. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. " Why should i trust you?" Explaining the predictions of any classifer. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 1135-1144.
  51. Peter J. Rousseeuw. 1987. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. 20 (1987), 53-65. https://doi.org/10.1016/0377- 0427(87)90125-7 · DOI · Paper page
  52. Jefrey M. Rzeszotarski and Aniket Kittur. 2011. Instrumenting the crowd: using implicit behavioral measures to predict task performance. In Proceedings of the 24th annual ACM symposium on User interface software and technology (Santa Barbara, California, USA, 2011-10-16) (UIST '11). Association for Computing Machinery, 13-22. https://doi.org/10.1145/2047196.2047199 · DOI
  53. Maggi Savin-Baden and Claire Howell Major. 2012. Qualitative research: the essential guide to theory and practice. Routledge.
  54. Erich Schubert, Jörg Sander, Martin Ester, Hans Peter Kriegel, and Xiaowei Xu. 2017. DBSCAN Revisited, Revisited: Why and How You Should (Still) Use DBSCAN. 42, 3 (2017), 1-21. https://doi.org/10.1145/3068335 · DOI
  55. D. Sculley and Bradley M. Pasanek. 2008. Meaning and mining: the impact of implicit assumptions in data mining for the humanities. Literary and Lin- guistic Computing 23, 4 (09 2008), 409-424. https://doi.org/10.1093/llc/fqn019 arXiv:https://academic.oup.com/dsh/article-pdf/23/4/409/3490781/fqn019.pdf · DOI
  56. Aaron Smith and Maeve Duggan. 2018. Online Harassment: What Americans Consider Crossing the Line. https://www.pewinternet.org/2018/01/04/crossing- the-line-what-counts-as-online-harassment/ CHI '22, April 29-May 5, 2022, New Orleans, LA, USA
  57. Guillermo Soberón, Lora Aroyo, Chris Welty, Oana Inel, Hui Lin, and Manfred Overmeen. 2013. Measuring crowd truth: disagreement metrics combined with worker behavior flters. In Proceedings of the 1st International Conference on Crowdsourcing the Semantic Web -Volume 1030 (Sydney, Australia, 2013-10-19) (CrowdSem'13). CEUR-WS.org, 45-58.
  58. Sara Owsley Sood, Elizabeth F. Churchill, and Judd Antin. 2012. Automatic identifcation of personal insults on social news sites. 63, 2 (2012), 270-285. https://doi.org/10.1002/asi.21690 · DOI
  59. Sara Steegen, Francis Tuerlinckx, Andrew Gelman, and Wolf Vanpaemel. 2016. Increasing Transparency Through a Multiverse Analysis. 11, 5 (2016), 702-712. https://doi.org/10.1177/1745691616658637 · DOI
  60. Harini Suresh and John V Guttag. 2019. A framework for understanding un- intended consequences of machine learning. arXiv preprint arXiv:1901.10002 (2019). · arXiv
  61. Anissa Tanweer, Emily Kalah Gade, P.M. Kraft, and Sarah K. Dreier. 2021. Why the Data Revolution Needs Qualitative Thinking. Harvard Data Science Review (30 7 2021). https://doi.org/10.1162/99608f92.eee0b0da https://hdsr.mitpress.mit.edu/pub/u9s6f22y. · DOI
  62. Yuan-Kai Wang. 2004. Context awareness and adaptation in mobile learning. In Wireless and Mobile Technologies in Education, 2004. Proceedings. The 2nd IEEE International Workshop on (2004). IEEE, 154-158.
  63. William Warner and Julia Hirschberg. 2012. Detecting Hate Speech on the World Wide Web. In Proceedings of the Second Workshop on Language in Social Media (Montréal, Canada, 2012-06). Association for Computational Linguistics, 19-26. http://www.aclweb.org/anthology/W12-2103
  64. Ellery Wulczyn, Nithum Thain, and Lucas Dixon. 2017. Ex Machina: Personal Attacks Seen at Scale. In Proceedings of the 26th International Conference on World Wide Web (Republic and Canton of Geneva, Switzerland, 2017) (WWW '17). International World Wide Web Conferences Steering Committee, 1391-1399. https://doi.org/10.1145/3038912.3052591 · DOI · Paper page

Authors
Cambo, S. A., & Gergle, D.
Affiliations
Northwestern University (US)
ORCID
Gergle, Darren
Venue
CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2022-04-29
Pages
1-19
DOI
10.1145/3491102.3501998
OpenAlex
W4225086340
Cited by
49
References
65
Citations by year
2026: 7 · 2025: 22 · 2024: 9 · 2023: 9 · 2022: 2
FWCI
10.43
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
CHI Conference on Human Factors in Computing Systems (publishedVersion)
Funders
Northwestern University
Topics
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Social Sciences › Sociology and Political Science › Qualitative Research Methods and Ethics
Keywords
positionality, data annotation, online communities, classifier development

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