The fabrication of synthetic data promises: Tracing emerging arenas of expectations and boundary work
Synthetic data, denoting artificially produced data that are used for data science tasks, are increasingly held as a promising solution to digital societies’ predicaments. While burgeoning research has investigated the implications of synthetic data, the fabrication of synthetic data promises remain...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-03-01
|
| Series: | Big Data & Society |
| Online Access: | https://doi.org/10.1177/20539517241307915 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Synthetic data, denoting artificially produced data that are used for data science tasks, are increasingly held as a promising solution to digital societies’ predicaments. While burgeoning research has investigated the implications of synthetic data, the fabrication of synthetic data promises remains understudied. This article draws on the sociology of expectations and the concept of boundary work to interrogate emerging arenas of expectations and attendant boundary work practices through which synthetic data promises are fabricated. To this end, it draws from a wide range of empirical materials, including scientific literatures, promissory reports, industry webinars, and interviews. First, it shows that scientific literatures reveal a strong increase in interest and three transformations in the framing of synthetic data in recent decades: from vernacular term to scientific concept, from possibility to inevitability, and from research technique to social promise. Second, it demonstrates that promissory organizations’ reports on synthetic data are generically performative as they circulate widely and constitute a source of authority for various stakeholders. Finally, it highlights three types of boundary work in relation to synthetic data: stipulations of its epistemic superiority, negotiations concerning most apt methodologies, and contestations regarding whether synthetic data are “fake.” I conclude by arguing that a sociology of expectations approach can productively question the hyperbolic promises attributed to synthetic data. Overall, this article contributes to germinal social studies of synthetic data by highlighting the constitutive role of expectations and boundary work in the fabrication of synthetic data promises. |
|---|---|
| ISSN: | 2053-9517 |