Latent Dirichlet allocation (LDA) topic models are increasingly being used in communication research. Yet, questions regarding reliability and validity of the approach have received little attention thus far. In applying LDA to textual data, researchers need to tackle at least four major challenges that affect these criteria: (a) appropriate pre-processing of the text collection; (b) adequate selection of model parameters, including the number of topics to be generated; (c) evaluation of the model's reliability; and (d) the process of validly interpreting the resulting topics. We review the research literature dealing with these questions and propose a methodology that approaches these challenges. Our overall goal is to make LDA topic modeling more accessible to communication researchers and to ensure compliance with disciplinary standards. Consequently, we develop a brief hands-on user guide for applying LDA topic modeling. We demonstrate the value of our approach with empirical data from an ongoing research project.
This article examines the agenda-building process in relation to three `counter-issues' in West Germany, focusing on often neglected processes within the media system, the role of the alternative press and the role of media opinion leaders. Our results show that the success of counter-issues at gaining coverage in the alternative press leads to a `spill-over effect': the issue spills like a wave from the alternative into the established media. Some liberal papers support this breakthrough. They function as media opinion leaders and initiate chain reactions within the media system. The spill-over effect is not limited to the topic itself. The established liberal media also adopt its frame of reference for presenting the issues from the alternative press. A typical issue `career', consisting of a latent and preparatory phase, an upswing phase, a climax and a downswing phase, will not occur when the issue is displaced by another more important problem. The dynamic agenda-building process is characterized by various interactions between the media, public and policy agenda.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.