par Dierickx, Laurence
Référence Computation + Journalism Symposium 2019 (01-02/02/2019: University of Miami)
Publication Publié, 2019-02-01
Poster de conférence
Résumé : This paper examines the causes of failures of automated news production. If technical factors have to be considered, such as bad data quality, the human factor remains essential, including within its social dimension. The proposed approach here is both theoretical and empirical. It is highlighted with the results of a case study conducted over one year. The project consisted of developing an automated news application about air quality within a Belgian newsroom, in order to provide real time information to the audiences as well as raw material for an investigative purpose.