Introduction: Big Data Content Analysis in (Online) Journalism Research

• In Event: Methodological Advances in Digital Content Analysis: Inductive and Deductive Approaches to ‘Big Data’ Research in Journalism Studies

Abstract

Big data analysis is not new: The visions of an automatic analysis of large masses of information are several decades old. However, the easy accessibility of digital content and the development of computer technology, as well as new methods and approaches in various disciplines (like computer linguistics, informatics, statistics, and social sciences), have enabled journalism researchers to expand the reach of their content analysis.
In the introductory presentation, the typical process of such an analysis will be outlined—from corpus construction, data retrieval, pre-processing and filtering, to the description of textual features and more complex analyses like topic modeling or time-based news emergence analyses. Several options for research will be introduced, ranging from fully automatic identification of textual elements, over topic modeling, clustering and time-based news flow analysis to the imitation of human coding behavior using machine learning. The process framework will serve as an orientation for the subsequent presentation of four individual projects that flesh out potential options for journalism research.

Author

• Thorsten Quandt, University of Muenster