• About the Konstanz Center for Data and Methods (CDM)

    Working with diverse data sets, advanced quantitative and computational methods lies at the heart of contemporary social science. At the Konstanz Center for Data and Methods we focus on developing, distributing, and teaching core competencies to address this challenge following a problem-driven approach: The choice of which data to collect or method to apply has to meet the demands of a given real-world problem or derive from theory-driven considerations. This pluralistic approach to data collection and analysis is reflected both in our research and teaching.

  • American Political Science Review

    Examining a Most Likely Case for Strong Campaign Effects

    A new study by Selb and Munzert revisits the question of how effective Adolf Hitler's public speeches were in garnering electoral support in Weimar Germany, 1927-1933. They collect extensive original data on five national elections preceding the dictatorship, and use a semi-parametric difference-in differences estimation strategy to account for often ignored endogeneity problems in the assessment of local campaign effects. In doing so, they also provide rare insight into the campaign strategy of the Nazi party. Their findings suggest that Hitler's speeches, while rationally targeted, had a negligible impact on the Nazis' electoral fortunes. The study was published in the American Political Science Review.

  • Review of International Political Economy

    Context-Driven Attitude Formation

    With colleagues at the University of Mannheim, we examined the difference between supporting free trade in the abstract and supporting specific trade agreements. Our analysis shows that in order to understand public support or opposition toward specific trade agreements, we have to move away from models using a fixed set of explanatory variables toward models that are more flexible and reactive to public discourse. Models traditionally used to understand preferences for or against international integration in the abstract might thus tell us little about support or opposition toward specific instances of these measures once they are politicized and subjects of public discourse. The study was published in Review of International Political Economy.

  • Journal of Conflict Resolution

    Integrating Conflict Event Data

    Together with colleagues at the University of Maryland/START we developed a new automated, transparent, reproducible methodology for integrating event data sets called MELTT. We show that using integrating data from four leading conflict event data sets (UCDP-GED, ACLED, GTD, SCAD) provides a more complete picture of conflict. We also apply multiple systems estimation to show that each of these data sets has substantial missingness in coverage. The study was published in the Journal of Conflict Resolution.

  • British Journal of Political Science

    Deliberative Abilities and Influence in a Transnational Deliberative Poll

    Together with colleagues at the Universities of Bern, Geneva and Stuttgart, we investigated the deliberative abilities of ordinary citizens in the context of 'EuroPolis', a transnational deliberative poll. The figure gives the item response functions, which relate the observable indicators from an an updated version of the Discourse Quality Index (DQI) with the latent deliberative abilities of individual citizens. The study was published in the British Journal of Political Science.

News

 

 

Funding for New Interdisciplinary Project on Media Bias

The Heidelberger Akademie der Wissenschaften has awarded a 3-year research grant for an interdisciplinary research project entitled "Fake News and Collective Decision Making: Rapid Automated Assessment of Media Bias". The project will be carried out jointly by the team of Karsten Donnay (Politics and Public Administration) and Bela Gipp (Computer Science).

New Article in International Journal on Digital Libraries

The article "Automated Identification of Media Bias in News Articles: An Interdisciplinary Literature Review" co-authored by Felix Hamborg, Karsten Donnay and Bela Gipp reviews the state-of-the-art in the automated study of bias in news media articles bringing together the latest insights from research in both social and computer science.

Further announcements

Events

Further dates