Automated Journalism 2.0: Event-driven narratives

Abstract

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.

Periodismo computacional: evolución, casos y herramientas

“…No obstante se requiere una nueva fase en la que es necesario centrarse en los modelos de datos para lograr la implementación y expansión del periodismo automatizado (Caswell;Dörr, 2018). Por ejemplo, en el informe El impacto de los datos en la era de la postverdad (Albert, 2017), profesionales de la comunicación analizan cómo afronta el sector la revolución de los datos y consideran que su uso es una de las formas de conseguir un periodismo de calidad, ya que permite luchar contra la postverdad.…”

Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics

“…The positive effect of conditioning shows that even with relatively superficial domain knowledge, clear improvements can be achieved. As such, we believe that, in addition to developing new and better text generation architectures, developing ways to better integrate such domain knowledge is also a fruitful path for future research [41, 42]. A final important and novel finding was the interaction between the generation model type and the presence or absence of conditioning in the model.…”

Locução automatizada e o rádio musical: primeiras aproximações

“…With the scope of innovations in journalistic practice, automation, one of its aspects, comes as argue Caswell and Dörr (2017), as a potential alternative to meet the desire for sustainable business models for news organizations and to respond to the growing economic pressure for an increase in productivity in the production of journalistic content.…”