Towards a responsible machine learning approach to identify forced labor in fisheries
This work addresses the problem of detecting forced labor in fisheries for regulatory bodies and human rights organizations, offering a tool to inform risk-based inspections, though it is incremental as it applies an existing method to a new domain.
The researchers tackled the challenge of identifying fishing vessels using forced labor by developing a positive-unlabeled learning algorithm based on vessel characteristics and movement patterns, achieving 89% recall for reported forced labor cases and estimating that up to ~28% of vessels may operate with forced labor, with higher rates in squid jiggers and longlines.
Many fishing vessels use forced labor, but identifying vessels that engage in this practice is challenging because few are regularly inspected. We developed a positive-unlabeled learning algorithm using vessel characteristics and movement patterns to estimate an upper bound of the number of positive cases of forced labor, with the goal of helping make accurate, responsible, and fair decisions. 89% of the reported cases of forced labor were correctly classified as positive (recall) while 98% of the vessels certified as having decent working conditions were correctly classified as negative. The recall was high for vessels from different regions using different gears, except for trawlers. We found that as much as ~28% of vessels may operate using forced labor, with the fraction much higher in squid jiggers and longlines. This model could inform risk-based port inspections as part of a broader monitoring, control, and surveillance regime to reduce forced labor. * Translated versions of the English title and abstract are available in five languages in S1 Text: Spanish, French, Simplified Chinese, Traditional Chinese, and Indonesian.