Enabling Trade-offs in Machine Learning-based Matching for Refugee Resettlement

Olberg, Nils; Seuken, Sven

doi:10.48550/arxiv.2203.16176

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the Random Forest Model was found to be the best model for mass movement sensitivity mapping. Olberg and Seuken (2022) examined the mechanisms which dealt with the settlement preferences of families regarding the relocation of immigrants and refugees in Switzerland and demonstrated that the CRV model was generally superior in terms of family welfare even in cases where the families had a certain order of preferences. In the study conducted by Nair et al (2019), simulated experiments were examined to estimate labor force export in Taiwan, Japan, and Korea, it was seen that in comparison to the real data in Taiwan, Korea, and Japan, Back-Propagation Neural Network findings yielded the closest results.…”

Section: Immigration Journeymentioning

confidence: 99%

Sinirlarin Ötesi̇ndeki̇ Di̇ji̇tal İzler: Göç Kri̇zi̇ Üzeri̇ne Si̇stemati̇k Bi̇r Derleme

YILMAZ,

ÖZCAN

2023

Sosyoloji Araştırmaları Dergisi

View full text Add to dashboard Cite

This study aimed to systematically examine the studies conducted and published on immigrants, asylum seekers, and refugees by using big data written in English. Articles were searched on Scholar, The Web of Science, ProQuest, Science Direct, PubMed and Scopus databases. The concept set centered around the concepts of immigration and big data was used in the surveys. In accordance with the PRISMA protocol principles, 49 articles were examined according to the inclusion and exclusion criteria among 258 articles obtained from the relevant databases until the end of December 2022. The reviewed articles were categorized under the headings of “topics examined”, “dataset”, “analyses”, “software used” and “key findings”. The studies provide indications on how to obtain information about this population, which is difficult to reach group especially due to its massiveness, using big data tools. In the findings, it has been seen that studies based on big data on immigrants, asylum seekers and refugees contribute to facilitating the integration of these groups into the target country. Also, it has been revealed that these studies may lead to undesirable results in terms of violating the confidentiality of research groups, producing labeling, and increasing surveillance for these groups. In addition to these, it has been found that these studies have methodological handicaps in terms of representativeness, accuracy, excessive homogenization, and easy generalization. It is thought that the findings of the study will shed light on the international migration and refugee policies to be carried out using big data analysis tools.

show abstract

Section: Immigration Journeymentioning

confidence: 99%