Christian Arnold

Christian Arnold, Andreas Küpfer

When photographers and other editors of image material produce an image, they make a statement about what matters by situating some objects in the foreground and others in the background. While this prominence of objects is a key analytical category to qualitative scholars, recent quantitative approaches to automated image analysis have not yet made this important distinction but treat all areas of an image similarly. We suggest carefully considering objects' prominence as an essential step in analyzing images as data. Its modeling requires defining an object and operationalizing and measuring how much attention a human eye would pay. Our approach combines qualitative analyses with the scalability of quantitative approaches. Exemplifying object prominence with different implementations -- object size and centeredness, the pixels' image depth, and salient image regions -- we showcase the usefulness of our approach with two applications. First, we scale the ideology of eight US newspapers based on images. Second, we analyze the prominence of women in the campaign videos of the U.S. presidential races in 2016 and 2020. We hope that our article helps all keen to study image data in a conceptually meaningful way at scale.

Christian Arnold, Andreas Küpfer

Political scientists increasingly analyze multimodal data. However, the effective analysis of such data requires aligning information across different modalities. In our paper, we demonstrate the significance of such alignment. Informed by a systematic review of 2,703 papers, we find that political scientists typically do not align their multimodal data. Introducing a decision tree that guides alignment choices, our framework highlights alignment's untapped potential and provides concrete advice in research design and modeling decisions. We illustrate alignment's analytical value through two applications: predicting tonality in U.S. presidential campaign ads and cross-modal querying of German parliamentary speeches to examine responses to the far-right AfD.

Christian Arnold, Marcel Neunhoeffer

Recent advances in generating synthetic data that allow to add principled ways of protecting privacy -- such as Differential Privacy -- are a crucial step in sharing statistical information in a privacy preserving way. But while the focus has been on privacy guarantees, the resulting private synthetic data is only useful if it still carries statistical information from the original data. To further optimise the inherent trade-off between data privacy and data quality, it is necessary to think closely about the latter. What is it that data analysts want? Acknowledging that data quality is a subjective concept, we develop a framework to evaluate the quality of differentially private synthetic data from an applied researcher's perspective. Data quality can be measured along two dimensions. First, quality of synthetic data can be evaluated against training data or against an underlying population. Second, the quality of synthetic data depends on general similarity of distributions or specific tasks such as inference or prediction. It is clear that accommodating all goals at once is a formidable challenge. We invite the academic community to jointly advance the privacy-quality frontier.