PolText 2016 – International Conference on the Advances in Computational Analysis of Political Text was held on July, 14-16, 2016 at the Inter-University Center Dubrovnik. It is the first interdisciplinary conference organized by the Center for Empirical Research in Political Science within the project “Political Priorities in Croatia (1990-2015)”. The conference was organized in cooperation with the University of Edinburgh, University of Oslo, and the TakeLab research group (Faculty of Electrical Engineering and Computing, University of Zagreb). Researchers from various universities across the world – Delaware, Arizona, Minnesota, Michigan, Aarhus, Zürich, Amsterdam, Strathclyde, Montréal, Ottawa, Oslo, Konstanz, Göteborg, Glasgow, Berkeley, East Anglia, Mannheim, London (LSE), Edinburgh, St. Louis and Zagreb – presented their papers.
Technological developments, digital media, and advances in open government practices have made a vast amount of information available for social scientists. Most of this information is available as text. News portals disseminate political stories at unprecedented rates, politicians and political elites advertise their own messages through social media outlets and crowdsourcing provides new affordable and quick venues for asking citizens what they think about politics. With political texts at our fingertips, vexing research questions are emerging.
Extracting, organizing, and analyzing large amounts of textual information can be quite resource-intensive with many political scientists lacking the skills necessary for dealing with such data. Fortunately, recent developments of cutting edge computational technologies such as automatic language processing, machine learning, and information extraction techniques has made research utilizing text-as-data more accessible and appealing.
On the other hand, computational scholars equipped with novel technologies and linguistic solutions often have less experience with social science theories and less contextual knowledge about political data. There is a mutual benefit in connecting disparate worlds of computational text analysis and political science in analyzing political science research problems. The aim of this conference was to facilitate this multidisciplinary cooperation.