Citizens’ opinions about politicians are shaped by their perceptions of politicians’ personalities, characters, and traits. While prior research has investigated the traits voters value in politicians, less attention has been given to the traits politicians project in their public communication. This may stem from challenges in defining politicians’ public personality traits and measuring them at scale using computational text analysis. To address this challenge, we propose a computational approach that builds on public statements (personality cues) to infer politicians’ personalities from textual data. To do so, we operationalize two key political traits—agency and communion—using a theory-driven, domain-specific framework. We then compare various computational text analysis methods for extracting these traits from a large corpus of politicians’ parliamentary speeches, social media posts, and interviews. We validate our approach using a comprehensive set of human-labeled data, functional tests, and analyses of how prominently personality traits appear in the statements of German politicians and in the 2024 U.S. presidential debate between Donald Trump and Kamala Harris. Our findings indicate that prompting based techniques, particularly those leveraging advanced models such as DeepSeek-V3, outperform supervised and semisupervised methods. These results point to promising directions for advancing political psychology.

With ambitious action required to achieve global climate mitigation goals, climate change has become increasingly salient in the political arena. This article presents a dataset of climate change salience in 1,792 political manifestos of 620 political parties across different party families in forty-five OECD, European, and South American countries from 1990 to 2022. Importantly, our measure uniquely isolates climate change salience, avoiding the conflation with general environmental and sustainability content found in other work. Exploiting recent advances in supervised machine learning, we developed the dataset by fine-tuning a pre-trained multilingual transformer with human coding, employing a resource-efficient and replicable pipeline for multilingual text classification that can serve as a template for similar tasks. The dataset unlocks new avenues of research on the political discourse of climate change, on the role of parties in climate policy making, and on the political economy of climate change. We make the model and the dataset available to the research community.

Politicians appeal to social groups to court their electoral support. However, quantifying which groups politicians refer to, claim to represent, or address in their public communication presents researchers with challenges. We propose a supervised learning approach for extracting group mentions from political texts. We first collect human annotations to determine the passages of a text that refer to social groups. We then fine-tune a transformer language model for contextualized supervised classification at the word level. Applied to unlabeled texts, our approach enables researchers to automatically detect and extract word spans that contain group mentions. We illustrate our approach in two applications, generating new empirical insights into how British parties use social groups in their rhetoric. Our method allows for detecting and extracting mentions of social groups from various sources of texts, creating new possibilities for empirical research in political science.

Over the past 20–30 years, women’s parties have consistently formed across Europe, aiming to improve women’s substantive representation by politicizing gender issues. Despite their potential impact on the policy agenda, empirical knowledge of the full range and scope of issues these parties mobilize is limited. This paper presents a novel mixed-method text analysis of the issue concerns in an original dataset of European women’s parties’ manifestos spanning a 30-year period. I find that parties across contexts share concerns in social justice and social policy. However, two subtypes of women’s party can be differentiated based on issue focus and framing. Essentialist women’s parties predominantly represent women’s material interests, whereas feminist parties additionally tackle structural gender inequality issues, including gender-based violence and human security. These findings provide a foundation for incorporating women’s parties into growing research on party competition over gender issues.

Human language is increasingly written rather than just spoken, primarily due to the proliferation of digital technology in modern life. This trend has enabled the creation of generative artificial intelligence (AI) trained on corpora containing trillions of words extracted from text on the internet. However, current language theory inadequately addresses digital text communication’s unique characteristics and constraints. This paper systematically analyzes and synthesizes existing literature to map the theoretical landscape of digitized language. The evidence demonstrates that, parallel to spoken language, features of written communication are frequently correlated with the socially constructed demographic identities of writers, a phenomenon we refer to as “digital accents.” This conceptualization raises complex ontological questions about the nature of digital text and its relationship to social identity. The same line of questioning, in conjunction with recent research, shows how generative AI systematically fails to capture the breadth of expression observed in human writing, an outcome we call “homogeneity-by-design.” By approaching text-based language from this theoretical framework while acknowledging its inherent limitations, social scientists studying language can strengthen their critical analysis of AI systems and contribute meaningful insights to their development and improvement.

While researchers often study message features like moral content in text, such as party manifestos and social media posts, their quantification remains a challenge. Conventional human coding struggles with scalability and intercoder reliability. While dictionary-based methods are cost-effective and computationally efficient, they often lack contextual sensitivity and are limited by the vocabularies developed for the original applications. In this paper, we present an approach to construct “vec-tionaries” that boost validated dictionaries with word embeddings through nonlinear optimization. By harnessing semantic relationships encoded by embeddings, vec-tionaries improve the measurement of message features from text, especially those in short format, by expanding the applicability of original vocabularies to other contexts. Importantly, a vec-tionary can produce additional metrics to capture the valence and ambivalence of a message feature beyond its strength in texts. Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and to produce measurements better aligned with crowdsourced human assessments. Furthermore, additional metrics from the vec-tionary unveiled unique insights that facilitated predicting downstream outcomes such as message retransmission.

Political communication on immigration is often highly moralized, with parties making claims to fundamental beliefs about right and wrong. Yet, what drives parties to use this rhetoric remains unexplored. Contributing to research on parties’ positional shifts on immigration, this study examines their strategic use of moral language in immigration discourse. To this end, we develop multilingual moral dictionaries to analyze parliamentary immigration speeches from eight Western democracies over six decades. While party-level factors do not explain moral language use, increased elite polarization on the issue is associated with greater moralization among all parties. Qualitative analysis shows that moral language is used overwhelmingly to attack political opponents, highlighting its divisive nature. These findings serve as a corrective to the notion that extreme, anti-immigrant, opposition parties are the main drivers of the moralization of immigration; instead, the broader political climate crucially shapes party incentives to (de)moralize.

Whether a topic is seen in a moral or moral-emotional light has significant political implications. Yet, we lack knowledge about the process of moralization: Who defines the way topics are communicated about? Where prior research has investigated the relative power of different actors to place a topic on the agenda or shape opinions, we study who sets the moral and moral-emotional tone of debate. To do so, we zoom in on immigration discourse in Germany and analyze fine-grained social media data from politicians, political parties, newspapers, and members of the public over a period of more than four years. After employing a transformer model to identify moral and moral-emotional appeals, we use structural vector autoregression models to demonstrate the important role of radical-right challengers in shaping public discourse in a negative moral-emotional direction. The results inform theories of moralization and political entrepreneurship.

Software now allows archaeologists to document excavations in more detail than ever before through rich, born-digital datasets. In comparison, paper documentation of past excavations (a valuable corpus of legacy data) is prohibitively difficult to work with. This pilot study explores creating custom software to digitize paper field notes from the 1970s excavations of the Gulkana site into machine-readable text and maps to be compatible with born-digital data from subsequent excavations in the 1990s. This site, located in Alaska's Copper River Basin, is important to archaeological understanding of metalworking innovation by precontact Northern Dene people, but is underrepresented in the literature because no comprehensive map of the site exists. The process and results of digitizing this corpus are presented in hopes of aiding similar efforts by other researchers.

How often, and in what contexts, have archaeologists discussed racism over the last four decades? Do societal events lead to sustained discussions of racism among the academic community? Here, the authors seek to answer these questions by applying computational text analysis methods to 68176 abstracts from 41 meetings of the Society for American Archaeology. Discussions of racism are found to be rare—usually a passing mention in the context of broader social issues. Historical archaeologists have addressed racism more frequently than other archaeologists. The results form a baseline against which the discipline's engagement with racism as a research theme and with anti-racist strategies might be tracked.