Metraipolis › archive › dc_fc76250f109c
Spotting (and Missing) Algorithmic Bias: Investigating User Understanding in a Fairness Assessment Tool — arXiv:2609.35781
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35781
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:27:35.659Z
- SHA-256 of the archived text
130760cc13d71fe3590aebe41897bee49a057bc067571687eac9609f231ef139- Stable URL of this page
https://metraipolis.com/documento/dc_fc76250f109c
How to cite
Spotting (and Missing) Algorithmic Bias: Investigating User Understanding in a Fairness Assessment Tool — arXiv:2609.35781 — arXiv (en), https://arxiv.org/abs/2609.35781 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc76250f109c (Metraipolis archive dc_fc76250f109c, sha256 130760cc13d71fe3590aebe41897bee49a057bc067571687eac9609f231ef139)
BibTeX
@misc{dcfc76250f109c,
title = {Spotting (and Missing) Algorithmic Bias: Investigating User Understanding in a Fairness Assessment Tool — arXiv:2609.35781},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35781},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc76250f109c; sha256 130760cc13d71fe3590aebe41897bee49a057bc067571687eac9609f231ef139},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35781. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fairness metric selection is typically left to data scientists, but which biases are problematic and which metric captures them best depends on stakeholders' experience and domain knowledge. This calls for involving non-technical stakeholders, but the research prototypes built for this purpose so far have not tested whether these stakeholders form accurate mental models of the metrics they interact with or can act on them to identify biases. We present FairAware, a fairness assessment tool co-designed with Human Resources (HR) domain experts. We evaluate stakeholders' understanding through a mixed-methods study with 70 participants (35 HR employees, 35 job seekers), measuring objective and subjective understanding, cognitive load, bias identification accuracy, and open-ended feedback. Most participants correctly identified the most disadvantaged group, with task duration being the only significant predictor. We also found a gap between subjective and objective understanding, with both groups performing similarly across all measures. These results suggest that fairness assessment tools for non-experts are usable for identifying biases but need built-in checks on understanding before stakeholders make higher-stakes decisions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.35781 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:58:50.321Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).