Computational Communication Research - Volume 1, Issue 1, 2019

Computational Communication Research (CCR) is a new open access journal dedicated to publishing high quality computational research in communication science. This editorial introduction describes the role that we envision for the journal. First, we explain what computational communication science is and why a new journal is needed for this subfield. Then, we elaborate on the type of research this journal seeks to publish, and stress the need for transparent and reproducible science. The relation between theoretical development and computational analysis is discussed, and we argue for the value of null-findings and risky research in additive science. Subsequently, the (experimental) two-phase review process is described. In this process, after the first double-blind review phase, an editor can signal that they intend to publish the article conditional on satisfactory revisions. This starts the second review phase, in which authors and reviewers are no longer required to be anonymous and the authors are encouraged to publish a preprint to their article which will be linked as working paper from the journal. Finally, we introduce the four articles that, together with this Introduction, form the inaugural issue.

This article introduces the interface for communication research (iCoRe) to access, explore, and analyze the Global Database of Events, Language, and Tone (GDELT; Leetaru & Schrodt, 2013). GDELT provides a vast, open source, and continuously updated repository of online news and event metadata collected from tens of thousands of news outlets around the world. Despite GDELT’s promise for advancing communication science, its massive scale and complex data structures have hindered efforts of communication scholars aiming to access and analyze GDELT. We thus developed iCoRe, an easy-to-use web interface that (a) provides fast access to the data available in GDELT, (b) shapes and processes GDELT for theory-driven applications within communication research, and (c) enables replicability through transparent query and analysis protocols. After providing an overview of how GDELT’s data pertain to addressing communication research questions, we provide a tutorial of utilizing iCoRe across three theory-driven case studies. We conclude this article with a discussion and outlook of iCoRe’s future potential for advancing communication research.

To disseminate their stories efficiently via social media, news organizations make decisions that resemble traditional editorial decisions. However, the decisions for social media may deviate from traditional ones because they are often made outside the newsroom and guided by audience metrics. This study focuses on selective link sharing as quasi-gatekeeping on Twitter – conditioning a link sharing decision about news content. It illustrates how selective link sharing resembles and deviates from gatekeeping for the publication of news stories. Using a computational data collection method and a machine learning technique called Structural Topic Model (STM), this study shows that selective link sharing generates a different topic distribution between news websites and Twitter and thus significantly revokes the specialty of news organizations. This finding implies that emergent logic, which governs news organizations’ decisions for social media, can undermine the provision of diverse news.

A lot of modern media use is guided by algorithmic curation, a phenomenon that is in desperate need of empirical observation, but for which adequate methodological tools are largely missing. To fill this gap, computational observation offers a novel approach—the unobtrusive and automated collection of information encountered within algorithmically curated media environments by means of a browser plug-in. In contrast to prior methodological approaches, browser plug-ins allow for reliable capture and repetitive analysis of both content and context at the point of the actual user encounter. After discussing the technological, ethical, and practical considerations relevant to this automated solution, we present our open-source browser plug-in as an element in an adequate multi-method design, along with potential links to panel surveys and content analysis. Ultimately, we present a proof-of-concept study in the realm of news exposure on Facebook; we successfully deployed the plug-in to Chrome and Firefox, and we combined the computational observation with a two-wave panel survey. Although this study suffered from severe recruitment difficulties, the results indicate that the methodological setup is reliable and ready to implement for data collection within a variety of studies on media use and media effects.

Recommendation algorithms are widely used in online cultural markets to provide personalized suggestions for products like books and movies. At the heart of the commercial success of recommendation algorithms is their ability to make an accurate prediction of a target person’s preferences for previously unseen items. Can these algorithms also be used to predict which health messages an individual will evaluate favorably, and thereby provide effective tailored communication to the person? Although there is evidence that message tailoring enhances persuasion, little research has examined the effectiveness of recommendation algorithms for tailored health interventions aimed at promoting behavior change. We developed a message tailoring algorithm to select smoking-related public service announcements (PSAs) for smokers, and experimentally test its effectiveness in predicting a target smoker’s evaluations of PSAs and encouraging smoking cessation. The tailoring algorithm was constructed using multiple levels of data on smokers’ PSA rating history, individual differences, content features of the PSAs, and other smokers’ PSA ratings. We conducted a longitudinal online experiment to examine its efficacy in comparison to two non-tailored methods: “best in show” (choosing messages most preferred by other smokers) and “off the shelf” (random selection from eligible ads). The results showed that the tailoring algorithm produced more accurate predictions of smokers’ message evaluations than the simple-average method used for the “best in show” approach. Smokers who viewed PSAs recommended by the tailoring algorithm were more likely than those receiving a random set to evaluate the PSAs favorably and quit smoking. There was no significant difference between the “best in show” and “off the shelf” methods in message assessment and quitting behavior.