When no news is bad news - Detection of negative events from news media content

During the first wave of Covid-19 information decoupling could be observed in the flow of news media content. The corollary of the content alignment within and between news sources experienced by readers (i.e., all news transformed into Corona-news), was that the novelty of news content went down as media focused monotonically on the pandemic event. This all-important Covid-19 news theme turned out to be quite persistent as the pandemic continued, resulting in the, from a news media’s perspective, paradoxical situation where the same news was repeated over and over. This information phenomenon, where novelty decreases and persistence increases, has previously been used to track change in news media, but in this study we specifically test the claim that new information decoupling behavior of media can be used to reliably detect change in news media content originating in a negative event, using a Bayesian approach to change point detection.

[1]  Jing Hu,et al.  Culturomics meets random fractal theory: insights into long-range correlations of social and natural phenomena over the past two centuries , 2012, Journal of The Royal Society Interface.

[2]  John Salvatier,et al.  Probabilistic programming in Python using PyMC3 , 2016, PeerJ Comput. Sci..

[3]  E. Hannum.  INDIVIDUALS , 1934, Francis W. Parker School Studies in Education.

[4]  Jo Guldi.  The Measures of Modernity: The New Quantitative Metrics of Historical Change Over Time and Their Critical Interpretation , 2019, International Journal for History, Culture and Modernity.

[5]  Simon DeDeo,et al.  Individuals, institutions, and innovation in the debates of the French Revolution , 2017, Proceedings of the National Academy of Sciences.

[6]  P. Gustafson,et al.  Conservative prior distributions for variance parameters in hierarchical models , 2006 .

[7]  Melvin Wevers,et al.  Using Word Embeddings to Examine Gender Bias in Dutch Newspapers, 1950-1990 , 2019, LChange@ACL.

[8]  Simon Hengchen,et al.  ‘Workers of the World’? A Digital Approach to Classify the International Scope of Belgian Socialist Newspapers, 1885–1940 , 2019, Journal of European Periodical Studies.

[9]  Thomas V. Wiecki,et al.  Probabilistic Programming in Python using PyMC , 2015, 1507.08050.

[10]  J. V. Eijnatten,et al.  The Eurocentric Fallacy. A Digital-Historical Approach to the Concepts of ‘Modernity’, ‘Civilization’ and ‘Europe’ (1840–1990) , 2019, International Journal for History, Culture and Modernity.

[11]  James G. Scott,et al.  On the half-cauchy prior for a global scale parameter , 2011, 1104.4937.

[12]  Gerrit Voerman,et al.  Quantifying "Pillarization": Extracting Political History from Large Databases of Digitized Media Collections , 2016, HistoInformatics@DH.

[13]  Mike Kestemont,et al.  Mining the Twentieth Century’s History from the Time Magazine Corpus , 2014, LaTeCH@EACL.

[14]  David J. Newman,et al.  Probabilistic topic decomposition of an eighteenth-century American newspaper , 2006, J. Assoc. Inf. Sci. Technol..

[15]  Simon DeDeo,et al.  Exploration and exploitation of Victorian science in Darwin’s reading notebooks , 2015, Cognition.

[16]  Jianbo Gao,et al.  A curious case of entropic decay: Persistent complexity in textual cultural heritage , 2018, Digit. Scholarsh. Humanit..

[17]  Jonas Nielsen,et al.  Automated Compositional Change Detection in Saxo Grammaticus' Gesta Danorum , 2019, DHN.

[18]  Anja Bechmann,et al.  News Information Decoupling: An Information Signature of Catastrophes in Legacy News Media , 2021, ArXiv.