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.

No abstract

Topic modeling enables researchers to explore large document corpora. Large corpora, however, can be extremely costly to model in terms of time and computing resources. In order to circumvent this problem, two techniques have been suggested: (1) to model random document samples, and (2) to prune the vocabulary of the corpus. Although frequently applied, there has been no systematic inquiry into how the application of these techniques affects the respective models. Using three empirical corpora with different characteristics (news articles, websites, and Tweets), we systematically investigated how different sample sizes and pruning affect the resulting topic models in comparison to models of the full corpora. Our inquiry provides evidence that both techniques are viable tools that will likely not impair the resulting model. Sample-based topic models closely resemble corpus-based models if the sample size is large enough (> 10,000 documents). Moreover, extensive pruning does not compromise the quality of the resultant topics.

We propose a methodological approach to analyze the content of hyperlink networks which represent networked public spheres on the Internet. Using the case of the food safety movement in the United States, we demonstrate how to generate a hyperlink network with the web crawling tool Issue Crawler and merge it with the results of a probabilistic topic model of the network’s content. Combining hyperlink networks and content analysis allows us to interpret such a network in its entirety and with regard to the mobilizing potentials of specific sub-issues of the movement. We focus on two specific sub-issues in the food safety network, genetically modified food and food control, in order to trace the involved websites and their interlinking structures, respectively.

No abstract