American Behavioral Scientist, Ahead of Print.
What is the most optimal way of creating a gold standard corpus for training a machine learning system that is designed for automatically collecting protest information in a cross-country context? We show that creating a gold standard corpus for training and testing machine learning models on the basis of randomly chosen news articles from news archives yields better performance than selecting news articles on the basis of keyword filtering, which is the most prevalent method currently used in automated event coding. We advance this new bottom-up approach to ensure generalizability and reliability in cross-country comparative protest event collection from international and local news in different countries, languages, sources and time periods, which entails a large variety of event types, actors, and targets. We present the results of comparing our random-sample approach with keyword filtering. We show that the machine learning algorithms, and particularly state-of-the-art deep learning tools, perform much better when they are trained with the gold standard corpus from a randomly selected set of news articles from China, India, and South Africa. Finally, we also present our approach to overcome the major ethical issues that are intrinsic to protest event coding.