Abstract
The article proposes a new machine learning model for assessing media freedom. It postulates that when media are free, and journalists can safely criticize influential politicians, the relative political sentiment of articles featuring such politicians is negative. Conversely, when media are not free, sentiment is positive. Several applications of this model are presented using a dataset of 1 million articles from four post-Soviet countries and Poland. The analysis shows that in the 2017–20 period, the online media freedom was most heavily constrained in Kazakhstan and Belarus. Online media were free in Poland. The conducted media manipulation and censorship tests find such evidence in Russia, where influential politicians are less present in the online media in bad times. There are significant differences between post-socialist democracies and autocracies in media patterns during presidential elections.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
