Header

UZH-Logo

Maintenance Infos

Automated Journalism 2.0: Event-driven narratives. From simple descriptions to real stories


Caswell, David; Dörr, Konstantin (2017). Automated Journalism 2.0: Event-driven narratives. From simple descriptions to real stories. Journalism Practice:Epub ahead of print.

Abstract

This article introduces an exploratory computational approach to extending the realm of automated journalism from simple descriptions to richer and more complex event­driven 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 ab-sence of data models sufficient to encode the journalistic knowledge necessary for automatically writ-ing event-driven narratives. A detailed proposal addressing this constraint is presented, based on the representation of journalistic knowledge as structured event and structured narrative data. We de-scribe 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 com-mercial automated writing platform. Detailed examples of the use of each method are provided, in-cluding 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.

Abstract

This article introduces an exploratory computational approach to extending the realm of automated journalism from simple descriptions to richer and more complex event­driven 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 ab-sence of data models sufficient to encode the journalistic knowledge necessary for automatically writ-ing event-driven narratives. A detailed proposal addressing this constraint is presented, based on the representation of journalistic knowledge as structured event and structured narrative data. We de-scribe 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 com-mercial automated writing platform. Detailed examples of the use of each method are provided, in-cluding 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.

Statistics

Altmetrics

Downloads

72 downloads since deposited on 10 May 2017
72 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Mass Communication and Media Research
Dewey Decimal Classification:700 Arts
Language:English
Date:9 May 2017
Deposited On:10 May 2017 13:09
Last Modified:22 Nov 2017 13:46
Publisher:Taylor & Francis
ISSN:1751-2786
Additional Information:This is an Accepted Manuscript of an article published by Taylor & Francis in Journalism Practice on 2017, available online: http://wwww.tandfonline.com/10.1080/17512786.2017.1320773.
Publisher DOI:https://doi.org/10.1080/17512786.2017.1320773

Download

Download PDF  'Automated Journalism 2.0: Event-driven narratives. From simple descriptions to real stories'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 1MB
View at publisher