This article introduces an exploratory computational approach to extending the realm of automated journalism from simple descriptions to richer and more complex event driven narratives, based on original applied research in structured journalism. The practice of automated journalism is reviewed and a major constraint on the potential to automate journalistic writing is identified, namely the absence of data models sufficient to encode the journalistic knowledge necessary for automatically writing eventdriven narratives. A detailed proposal addressing this constraint is presented, based on the representation of journalistic knowledge as structured event and structured narrative data. We describe a prototyped database of structured events and narratives, and introduce two methods of using event and narrative data from the prototyped database to provide journalistic knowledge to a commercial automated writing platform. Detailed examples of the use of each method are provided, including a successful application of the approach to stories about car chases, from initial data reporting through to automatically generated text. A framework for evaluating automatically generated event-driven narratives is proposed, several technical and editorial challenges to applying the approach in practice are discussed, and several high-level conclusions about the importance of data structures in automated journalism workflows are provided.
Computational journalism is defined as a practice in which journalistic knowledge is represented computationally, as systems of discrete categories or as numbers, during reporting, analysis, distribution, or consumption. This is in contrast to traditional journalism in which journalistic knowledge is reported, analyzed, distributed, and consumed as natural language text or speech, whether in analog or digital media. Journalistic knowledge is defined as externally represented knowledge that is under human editorial control in the service of journalistic values. In this entry, we review the development of computational journalism as a practice and as a field of study before examining the inherent tensions which structure it as a field.
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.