Abstract
Asylum is a legal protection granted by a state to individuals who demonstrate a well-founded fear
of persecution or who face real risk of being subjected to torture in their country. However, asylum
adjXdicaWion ofWen dependV on Whe deciVion makeU¶V VXbjecWiYe aVVeVVmenW of Whe applicanW¶V
credibility. To investigate potential sources of bias in asylum adjudication practices researchers
have used statistics and machine learning models, finding significant sources of variation with
respect to a number of extra-legal variables. In this paper, we analyse an original dataset of Danish
asylum decisions from the Refugee Appeals Board to understand the variables that explain Danish
Adjudication. We train a number of classifiers and, while all classifiers agree that candidate
credibility is the single most important variable, we find that performance and variable importance
change significantly depending on whether data imbalance and temporality are taken into account.
We discuss the implications of our findings with respect to the theory and practice of predicting and
explaining asylum adjudication.
of persecution or who face real risk of being subjected to torture in their country. However, asylum
adjXdicaWion ofWen dependV on Whe deciVion makeU¶V VXbjecWiYe aVVeVVmenW of Whe applicanW¶V
credibility. To investigate potential sources of bias in asylum adjudication practices researchers
have used statistics and machine learning models, finding significant sources of variation with
respect to a number of extra-legal variables. In this paper, we analyse an original dataset of Danish
asylum decisions from the Refugee Appeals Board to understand the variables that explain Danish
Adjudication. We train a number of classifiers and, while all classifiers agree that candidate
credibility is the single most important variable, we find that performance and variable importance
change significantly depending on whether data imbalance and temporality are taken into account.
We discuss the implications of our findings with respect to the theory and practice of predicting and
explaining asylum adjudication.
Originalsprog | Engelsk |
---|---|
Titel | ICAIL: International Conference on Artificial Intelligence and Law |
Antal sider | 10 |
Forlag | Association for Computing Machinery |
Publikationsdato | 2023 |
Sider | 217-226 |
ISBN (Elektronisk) | 9798400701979 |
DOI | |
Status | Udgivet - 2023 |
Begivenhed | 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Braga, Portugal Varighed: 19 jun. 2023 → 23 jun. 2023 |
Konference
Konference | 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 |
---|---|
Land/Område | Portugal |
By | Braga |
Periode | 19/06/2023 → 23/06/2023 |
Sponsor | Centro Algoritmi, et al., International Association for Artificial Intelligence and Law, JUSGOV - Research Center in Justice and Governance, Universidade do Minho Informatics Department at Engineering School, Universidade do Minho Law School |
Navn | 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference |
---|
Bibliografisk note
Publisher Copyright:© ICAIL 2023. All rights reserved.