Mapping News Geography: A Computational Framework for Classifying Local Media Through Geographic Coverage Patterns

Simona Bisiani; Agnes Gulyas; Bahareh Heravi

doi:10.63744/PmuIcNvSnDuo

Mapping News Geography: A Computational Framework for Classifying Local Media Through Geographic Coverage Patterns

Simona Bisiani, Agnes Gulyas Bahareh Heravi

Anthology of Computers and the Humanities, Vol.3, pp.861-882

Anthology of Computers and the Humanities, 3

Sixth Conference on Computational Humanities Research (CHR 2025) (Luxembourg City, Luxembourg, 09/12/2025–12/12/2025)

21/11/2025

: https://doi.org/10.63744/PmuIcNvSnDuo

local journalism

spatial analysis

coverage

geoparsing

unsupervised learning

computational journalism

geographic coverage

media geography

outlet classification

content analysis

clustering algorithms

news localisation

This study introduces a novel computational framework for defining local news outlets through their geographic coverage patterns. This approach addresses the growing disconnect between legacy spatial markers (e.g., newsroom location or circulation cut-offs) and the geographic dimension of news coverage amidst media ownership consolidation and digital transformation. We develop a four-step pipeline consisting of data sampling, geoparsing, feature engineering, and clustering analysis. Our approach employs large language models for toponym disambiguation and develops eight spatial metrics across four dimensions: spatial extent, administrative reach, spatial heterogeneity, and distance decay. We test this pipeline on a sample of more than 465,000 articles from 360 UK digital local news outlets. Clustering analysis of more than 1.3 million locations reveals six distinct outlet types, ranging from hyperlocal and metropolitan to national outlets. This classification reflects different scales and structures of news provision in the UK’s evolving media landscape. The method offers a scalable, open-source approach for mapping local news coverage and understanding the scope of local news providers as a function of their coverage, with implications for media geography and policy, ownership studies, and the computational humanities.

(2)

url

https://doi.org/10.63744/PmuIcNvSnDuo

Published (Version of record)

url

https://2025.computational-humanities-research.org/

Event Website Conference website

: Mapping News Geography: A Computational Framework for Classifying Local Media Through Geographic Coverage Patterns
: Simona Bisiani (Author) - University of Surrey, Surrey Institute for People-Centred AI
Agnes Gulyas (Author) - Canterbury Christ Church University
Bahareh Heravi (Author) - University of Surrey, Surrey Institute for People-Centred AI
: Anthology of Computers and the Humanities, Vol.3, pp.861-882
: Sixth Conference on Computational Humanities Research (CHR 2025) (Luxembourg City, Luxembourg, 09/12/2025–12/12/2025)
: Anthology of Computers and the Humanities; 3
: Association for Computers and the Humanities; Austin, Texas, U.S.A.
: 21/11/2025
: GeoDS 3139, ES/Z504464/1, Economic and Social Research Council (United Kingdom, Swindon) - ESRC
: The classification of census tracts data used in this research have been provided by the Geographic Data Service, a Smart Data Research UK Investment, under project ID GeoDS 3139, ES/Z504464/1.
: 991148795802346
: Surrey Institute for People-Centred AI; Surrey Business School; School of Computer Science & Electronic Engineering
: English
: Conference proceeding
: The analyses in this study can be reproduced through the following, permanently-stored, openaccess code repository: https://doi.org/10.7910/DVN/T7SE5F. We have also developed a platform for users to interact with the data and explore how different outlets’ coverage spread across a map: https://simonabisiani-local-news-map-explorer.share.connect. posit.cloud/.