Current political developments worldwide illustrate that research on democratic backsliding is as important as ever. A recent exchange in Political Science & Politics (February 2024) highlighted again that the measurement of democracy remains a challenge. With many democracy indicators consisting of subjective assessments rather than factual observations, trends in democracy over time could be due to human biases in the coding of these indicators rather than empirical facts. This article leverages two cutting-edge Large Language Models (LLMs) for the coding of democracy indicators from the V-Dem project. With access to huge amounts of information, these models may be able to rate the many “soft” characteristics of regimes at substantially lower costs. Whereas LLM-generated codings largely align with expert coders for many countries, we show that when these models deviate from human assessments, they do so in different but consistent ways. Some LLMs are too pessimistic and others consistently overestimate the democratic quality of these countries. Although the combination of the two LLM codings can alleviate this concern, we conclude that it is difficult to replace human coders with LLMs because the extent and direction of these attitudes is not known a priori.

Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. This paper presents a two-level classification method that addresses this transparency problem. At the first stage, an image segmenter detects the objects present in the image and a feature vector is created from those objects. In the second stage, this feature vector is used as input for standard machine learning classifiers to discriminate between images. We apply this method to a new dataset of more than 140,000 images to detect which ones display political protest. This analysis demonstrates three advantages to this paper’s approach. First, identifying objects in images improves transparency by providing human-understandable labels for the objects shown on an image. Second, knowing these objects enables analysis of which distinguish protest images from non-protest ones. Third, comparing the importance of objects across countries reveals how protest behavior varies. These insights are not available using conventional computer vision classifiers and provide new opportunities for comparative research.

Ethnic movements continue to challenge state governments globally, with many ethnic conflicts revolving around the status of groups’ territories. Yet, politically mobilized ethnic groups vary considerably in their territorial demands: some press for increased autonomy or even outright secession, while others do not make such demands at all and prefer integration in the existing state. What explains this divergence in ethnic group demands with respect to the group's territorial status? We argue that the expected benefits of ethno-regional autonomy or secession compared to integration in a centralized state differ across distinct segments within the group as a function of three structural factors: heterogeneity in the group's income sources, cultural divisions, and territorial fragmentation, leading to disagreement over self-determination demands between different political organizations representing the same ethnic group. We test our argument using an expanded version of the Ethnic Power Relations–Organizations (EPR-O) dataset. Our pre-registered study finds support for one of our hypotheses: heterogeneity in groups’ income sources increases disagreement over self-determination demands. This finding sheds new light on the structural sources of internal divisions within ethno-political movements.