Hybrid Methodology: Combining Ethnography, Cognitive Science, and Machine Learning to Inform the Development of Context‐Aware Personal Computing and Assistive Technology

Abstract

Denotes co-first authors.The not-too-distant future may bring more ubiquitous personal computing technologies seamlessly integrated into people's lives, with the potential to augment reality and support human cognition. For such technology to be truly assistive to people, it must be context-aware. Human experience of context is complex, and so the early development of this technology benefits from a collaborative and interdisciplinary approach to researchwhat the authors call "hybrid methodology"-that combines (and challenges) the frameworks, approaches, and methods of machine learning, cognitive science, and anthropology. Hybrid methodology suggests new value ethnography can offer, but also new ways ethnographers should adapt their methodologies, deliverables, and ways of collaborating for impact in this space. This paper outlines a few of the data collection and analysis approaches emerging from hybrid methodology, and learnings about impact and team collaboration, that could be useful for applied ethnographers working on interdisciplinary projects and/or involved in the development of ubiquitous assistive technologies.

Conceptualising fairness: three pillars for medical algorithms and health equity

“… 19 30 Accordingly, evidence suggests that interdisciplinary or ‘hybrid’ teams support fairness-aware ML. 117 Domain experts, such as clinicians, social scientists or patient advocacy groups, have enhanced understandings of context situated bias, 114 116 118 support the curation of salient axes of difference, 119 and improve topic modelling and natural language processing models by aiding social bias detection. 120–122 For example, ‘computational ethnography’ is an approach to fairness-aware ML that emphasises the importance of a holistic understanding of any given dataset.…”

“…Furthermore, this bias is maintained by social, technical and political systems which persist despite efforts to redress model bias with technical means 19 30. Accordingly, evidence suggests that interdisciplinary or ‘hybrid’ teams support fairness-aware ML 117. Domain experts, such as clinicians, social scientists or patient advocacy groups, have enhanced understandings of context situated bias,114 116 118 support the curation of salient axes of difference,119 and improve topic modelling and natural language processing models by aiding social bias detection 120–122.…”

Predictive care: a protocol for a computational ethnographic approach to building fair models of inpatient violence in emergency psychiatry

“…Thus, to fully grasp the impact of predictive care for clinical practice and health equity, we extend on Cury et al' 'hybrid methodology'. 54 Hybrid methodologies combine (and challenge) the analytical frameworks and methods from multiple disciplines; in our case, computer science, medicine, anthropology, bioethics and psychology. [55][56][57] Our hybrid approach emphasises the importance of sharing perspectives, reflecting on tensions and being open to new ideas.…”

Ethnographic data in the age of big data: How to compare and combine

“…These tools are helpful in many social science settings, for example, to predict students’ academic performance (Bjerre-Nielsen et al, 2021), and can be integrated into algorithms that determine decisions based on the predictions. As argued in the introduction, machines can use data annotated by humans to learn to correctly recognize patterns and properties of a situation (Cury et al, 2019). Another use is to use ethnographic data as an input in the prediction, which will lead to better predictions (given that the ethnographic data included is relevant).…”

“…This is contrasted by the rapid commercial development of models created on data that combines big data with data annotated by humans. These models can often accurately infer the human annotation or judgment from the big data, for example, whether a post on social media contains violence, and recently also capture ethnographic descriptions of situations (Cury et al, 2019). Yet, beyond simply recreating such human annotation, little research has been dedicated to studying how to actively combine ethnographic fieldwork with “big data” using quantitative methods.…”