This working paper was written by Soline Aubry 1, Hansdeep Singh 2, Ivan Vlahinic 1, Abhimanyu Ramachandran 1, Sara Fischer 4, Robert O'Callaghan 1, Natalie Shoup 3, Jaspreet Singh 2, David Sangokoya 3, Gabriel Pestre 3, and Carson Martinez 3.
1 CKM ADVISORS; 2 ICAAD; 3 DATA POP ALLIANCE; 4 GLOBAL INSIGHT.
Please send any comments to firstname.lastname@example.org.
The United Nations (UN) Universal Periodic Review (UPR) is a process established by the Human Rights Council aiming to monitor and improve the human rights situation in each UN member state. In this study, we hypothesize that leveraging text mining and machine-learning algorithms is a viable strategy for monitoring gender discrimination in sentencing practices of Fiji’s judiciary system, which has been the object of recommendations from Norway and Belgium in the UPR cycles of 2010 and 2015, respectively.
When focusing on Violence Against Women and Girls (VAWG) in Fiji, two types of offenses are of specific interest: sexual assault (SA) and domestic violence (DV). Legal action in cases of sexual assault and domestic violence is governed by several different laws in Fiji, but studies have shown that discriminatory practices in how and when these laws are applied may in some instances undermine their effectiveness. Determining whether or not gender discrimination has a systematic impact on the outcome of these sentences requires extensive analysis of case law archives.
Our hope is that the outcomes of this study, designed as a collaborative effort between data scientists and lawyers with known expertise in the UPR process, will encourage to develop more systematic and quantitative methodologies to track the implementation of recommendations, resulting in an increased accountability of countries towards the UPR process.