# Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science

arXiv: https://arxiv.org/abs/2203.07031 · HTML: https://mlsanity.com/paper/2203.07031/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 101 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Problem Formulation and Fairness](https://mlsanity.com/paper/1901.02547/) (2019)
- ["What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness](https://mlsanity.com/paper/2011.02282/) (2020)
- [Empath: Understanding Topic Signals in Large-Scale Text](https://mlsanity.com/paper/1602.06979/) (2016)
- [Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms](https://mlsanity.com/paper/1801.06482/) (2018)
- [Like trainer, like bot? Inheritance of bias in algorithmic content moderation](https://mlsanity.com/paper/1707.01477/) (2017)
- [Peer to Peer Hate: Hate Speech Instigators and Their Targets](https://mlsanity.com/paper/1804.04649/) (2018)
- [CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement](https://mlsanity.com/paper/1808.06080/) (2018)
- [Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects](https://mlsanity.com/paper/2002.03389/) (2020)
- [Deep Learning for User Comment Moderation](https://mlsanity.com/paper/1705.09993/) (2017)
- [Antisocial Behavior in Online Discussion Communities](https://mlsanity.com/paper/1504.00680/) (2015)
- [Data Vision: Learning to See Through Algorithmic Abstraction](https://mlsanity.com/paper/2002.03387/) (2020)
- [Crowdsourcing Semantic Label Propagation in Relation Classification](https://mlsanity.com/paper/1809.00537/) (2018)

## Built on by (most cited first, 13 of 13)

- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [From Melting Pots to Misrepresentations: Exploring Harms in Generative AI](https://mlsanity.com/paper/2403.10776/) (2024)
- [The AI Incident Database as an Educational Tool to Raise Awareness of AI Harms: A Classroom Exploration of Efficacy, Limitations, & Future Improvements](https://mlsanity.com/paper/2310.06269/) (2023)
- [Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology](https://mlsanity.com/paper/2310.04529/) (2023)
- [Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance](https://mlsanity.com/paper/2406.17385/) (2024)
- [Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMs](https://mlsanity.com/paper/2506.02659/) (2025)
- [A Taxonomy of Challenges to Curating Fair Datasets](https://mlsanity.com/paper/2406.06407/) (2024)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- [False consensus biases AI against vulnerable stakeholders](https://mlsanity.com/paper/2407.12143/) (2024)
- [Cripping AI: Reimagining AI Through Lived Disability Experiences](https://mlsanity.com/paper/2605.02080/) (2026)
- [Abstracted Away: Resisting Alienation and Ungrounded Abstraction in AI Research Communities](https://mlsanity.com/paper/2608.08408/) (2026)
- [LLJ Cards: Best practices for the Use of LLMs as Judges](https://mlsanity.com/paper/2609.24516/) (2026)

## Abstract (arXiv)

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.