Speaker: Ana Macanovic, Utrecht University
Abstract: The emergence of big data and computational tools has introduced new possibilities for using large-scale textual sources in social science research. We discuss five computational text analysis methods that can help researchers analyze large quantities of textual data and discuss exemplary applications in recently published research. First, we show how dictionary methods can assist the quantification of concepts of interest in texts; then, we summarize the potential of using semantic text analysis to extract information on social actors, social actions, and relationships between them. We move on to explore how unsupervised machine learning clustering methods assist inductive exploration of underlying meanings and concepts present in texts and how supervised machine learning classification methods support replication of manual coding onto new data. Finally, we discuss how powerful language models can help us map complex meanings, explore the evolution of meanings over time, and follow the emergence of new concepts in texts. We conclude by emphasizing the important implications of using large datasets and computational methods to infer complex meaning from texts in social sciences. This talk builds on this recently published paper.