Predicting news deserts using supervised machine learning

Arijit Paladhi ()
Additional contact information
Arijit Paladhi: Indiana University

Journal of Computational Social Science, 2025, vol. 8, issue 2, No 20, 29 pages

Abstract: Abstract The decline of local newspapers has led to the emergence of news deserts—areas lacking access to critical local information—posing a threat to community engagement and democracy. This study aims to predict which U.S. counties are most at risk of becoming news deserts by developing machine learning models based on socioeconomic, geographic, and circulation data. Addressing class imbalance and data noise, we employed classifiers such as Logistic Regression, Random Forest, XGBoost, Support Vector Machines, K-Nearest Neighbors, and Naive Bayes, combined with resampling techniques like SMOTE, Tomek Links, SMOTETomek, SMOTEENN, and ADASYN. Our analysis found that XGBoost combined with ADASYN performed best, achieving an F2-Score of 0.486 and AUC-PR of 0.467 on test data. These results provide valuable insights for policymakers aiming to develop targeted interventions to preserve local media ecosystems and strengthen democratic processes.

Keywords: Computational social science; Local news; Local journalism; News deserts; Computational methods; Predictive modelling; Big data (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-025-00379-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:8:y:2025:i:2:d:10.1007_s42001-025-00379-7

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-025-00379-7

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().