Accelerating comparative research: Strategies for a language and context-sensitive multilingual text analysis

Dealing with large volumes of multilingual documents, social scientists across disciplines have a common interest in adapting the so popular text-as-data methods for exciting new applications in cross-lingual comparative research. This talk outlines the key challenges for studying social science related concepts in multilingual text collections with automated content analysis methods. By discussing the main methodological strategies for working with multilingual corpora and by presenting a language and context sensitive validation framework, the aim is then to equip researchers with guidance for their next comparative text-as–data research project.

The event is part of the Digitalization and Society lecture series.

Fabienne Lind is a Research Associate at the Computational Communication Science Lab at the University of Vienna.