How to better reduce measurement variability and bias introduced by subjectivity in crowdsourced labelling remains an open question. We introduce a theoretical framework for understanding how random error and measurement bias enter into crowdsourced annotations of subjective constructs. We then propose a pipeline that combines pairwise comparison labelling with Elo scoring, and demonstrate that it outperforms the ubiquitous majority-voting method in reducing both types of measurement error. To assess the performance of the labelling approaches, we constructed an agent-based model of crowdsourced labelling that lets us introduce different types of subjectivity into the tasks. We find that under most conditions with task subjectivity, the comparison approach produced higher f1 scores. Further, the comparison approach is less susceptible to inflating bias, which majority voting tends to do. To facilitate applications, we show with simulated and real-world data that the number of required random comparisons for the same classification accuracy scales log-linearly O(N log N) with the number of labelled items. We also implemented the Elo system as an open-source Python package.

Quantifying the amount of polarization is crucial for understanding and studying political polarization in political and social systems. Several methods are used commonly to measure polarization in social networks by purely inspecting their structure. We analyse eight of such methods and show that all of them yield high polarization scores even for random networks with similar density and degree distributions to typical real-world networks. Further, some of the methods are sensitive to degree distributions and relative sizes of the polarized groups. We propose normalization to the existing scores and a minimal set of tests that a score should pass in order for it to be suitable for separating polarized networks from random noise. The performance of the scores increased by 38%-220% after normalization in a classification task of 203 networks. Further, we find that the choice of method is not as important as normalization, after which most of the methods have better performance than the best-performing method before normalization. This work opens up the possibility to critically assess and compare the features and performance of different methods for measuring structural polarization.

Human trafficking is a global problem which impacts a countless number of individuals every year. In this project, we demonstrate how machine learning techniques and qualitative reports can be used to generate new valuable quantitative information on human trafficking. Our approach generates original data, which we release publicly, on the directed trafficking relationship between countries that can be used to reconstruct the global transnational human trafficking network. Using this new data and statistical network analysis, we identify the most influential countries in the network and analyze how different factors and network structures influence transnational trafficking. Most importantly, our methods and data can be employed by policymakers, non-governmental organizations, and researchers to help combat the problem of human trafficking.