On predicting and explaining asylum adjudication
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
On predicting and explaining asylum adjudication. / Piccolo, Sebastiano Antonio; Gammeltoft-Hansen, Thomas; Katsikouli, Panagiota; Slaats, Tijs.
ICAIL: International Conference on Artificial Intelligence and Law. Association for Computing Machinery, 2023. s. 217-226 (19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - On predicting and explaining asylum adjudication
AU - Piccolo, Sebastiano Antonio
AU - Gammeltoft-Hansen, Thomas
AU - Katsikouli, Panagiota
AU - Slaats, Tijs
N1 - Publisher Copyright: © ICAIL 2023. All rights reserved.
PY - 2023
Y1 - 2023
N2 - 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 adjudication often depends on the decision maker’s subjective assessment of the applicant’s 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.
AB - 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 adjudication often depends on the decision maker’s subjective assessment of the applicant’s 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.
KW - Asylum adjudication
KW - Data Imbalance
KW - Explanatory Modelling
KW - Predictive Modelling
U2 - 10.1145/3594536.3595155
DO - 10.1145/3594536.3595155
M3 - Article in proceedings
AN - SCOPUS:85177879156
T3 - 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference
SP - 217
EP - 226
BT - ICAIL: International Conference on Artificial Intelligence and Law
PB - Association for Computing Machinery
T2 - 19th International Conference on Artificial Intelligence and Law, ICAIL 2023
Y2 - 19 June 2023 through 23 June 2023
ER -
ID: 377063257