Lukas Birkenmaier

Lukas Birkenmaier, Claudia Wagner, Clemens Lechner

Guidance on how to validate computational text-based measures of social constructs is fragmented. While researchers generally acknowledge the importance of validating text-based measures, they often lack a shared vocabulary and a unified framework to do so. This paper introduces ValiText, a new validation framework designed to assist scholars in validly measuring social constructs in textual data. The framework is built on a conceptual foundation of validity in the social sciences, strengthened by an empirical review of validation practices in the social sciences and consultations with experts. Ultimately, ValiText prescribes researchers to demonstrate three types of validation evidence: substantive evidence (outlining the theoretical underpinning of the measure), structural evidence (examining the properties of the text model and its output) and external evidence (testing for how the measure relates to independent information). The framework is further supplemented by a checklist of validation steps, offering practical guidance in the form of documentation sheets that guide researchers in the validation process.

Lukas Birkenmaier, Laureen Sieber, Felix Bergstein

This paper presents a novel dataset of public broadcast interviews featuring high-ranking German politicians. The interviews were sourced from YouTube, transcribed, processed for speaker identification, and stored in a tidy and open format. The dataset comprises 99 interviews with 33 different German politicians across five major interview formats, containing a total of 28,146 sentences. As the first of its kind, this dataset offers valuable opportunities for research on various aspects of political communication in the (German) political contexts, such as agenda-setting, interviewer dynamics, or politicians' self-presentation.

Lukas Birkenmaier, Matthias Roth, Indira Sen

Computational text classification is a challenging task, especially for multi-dimensional social constructs. Recently, there has been increasing discussion that synthetic training data could enhance classification by offering examples of how these constructs are represented in texts. In this paper, we systematically examine the potential of theory-driven synthetic training data for improving the measurement of social constructs. In particular, we explore how researchers can transfer established knowledge from measurement instruments in the social sciences, such as survey scales or annotation codebooks, into theory-driven generation of synthetic data. Using two studies on measuring sexism and political topics, we assess the added value of synthetic training data for fine-tuning text classification models. Although the results of the sexism study were less promising, our findings demonstrate that synthetic data can be highly effective in reducing the need for labeled data in political topic classification. With only a minimal drop in performance, synthetic data allows for substituting large amounts of labeled data. Furthermore, theory-driven synthetic data performed markedly better than data generated without conceptual information in mind.