Simona Bisiani

Location mentions in local news are crucial for examining issues like spatial inequalities, news deserts and the impact of media ownership on news diversity. However, while geoparsing – extracting and resolving location mentions – has advanced through statistical and deep learning methods, its use in local media studies remains limited and fragmented due to technical challenges and a lack of practical frameworks. To address these challenges, we identify key considerations for successful geoparsing and review spatially oriented local media studies, finding over-reliance on limited geospatial vocabularies, limited toponym disambiguation and inadequate validation of methods. These findings underscore the need for adaptable and robust solutions, and recent advancements in fine-tuned large language models (LLMs) for geoparsing offer a promising direction by simplifying technical implementation and excelling at understanding contextual nuances. However, their application to U.K. local media – marked by fine-grained geographies and colloquial place names – remains underexplored due to the absence of benchmark datasets. This gap hinders researchers’ ability to evaluate and refine geoparsing methods for this domain. To address this, we introduce the Local Media UK Geoparsing (LMUK-Geo) dataset, a hand-annotated corpus of U.K. local news articles designed to support the development and evaluation of geoparsing pipelines. We also propose an LLM-driven approach for toponym disambiguation that replaces fine-tuning with accessible prompt engineering. Using LMUK-Geo, we benchmark our approach against a fine-tuned method. Both perform well on the novel dataset: the fine-tuned model excels in minimising coordinate-error distances, while the prompt-based method offers a scalable alternative for district-level classification, particularly when relying on predictions agreed upon by multiple models. Our contributions establish a foundation for geoparsing local media, advancing methodological frameworks and practical tools to enable systematic and comparative research.

The strategic restructuring of UK corporate-owned local newspapers through regional hubs has enabled content homogenisation across titles and centralised editorial operations away from communities, raising concerns about democratic commitment and place-based relevance in local news coverage. This study adapts an established framework for assessing journalistic performance — encompassing locality, originality, and coverage of critical information needs — to provide the first longitudinal evidence of how these dimensions evolve under organisational restructuring at Reach plc, the UK’s largest publisher. Using a panel of 27 newspapers across seven regional hubs observed monthly in 2019, 2022, and 2025, we find that: (1) local CIN content is declining while homogenisation intensifies; (2) homogenisation is applied primarily to lifestyle and geographically generic coverage, crowding out — rather than diluting — local CIN content; and (3) content shared within regional hubs remains markedly more local and CIN-aligned than group-wide content, which instead is largely lifestyle-oriented and non-geographic. Notably, regional hubs, once the main organising principle for content sharing, are losing influence to group-wide homogenisation — a trend coinciding with the creation of a national Content Hub and AI-assisted editorial tools. The findings point towards a downward trajectory in corporate-owned local journalism’s commitment to place and substantive coverage, with implications for community representation, democratic accountability, and media plurality policy, and contribute to a UK-specific theorisation of ‘zombie’ papers.

A paper associated with the dataset has been published at: https://doi.org/10.1609/icwsm.v19i1.35940UKTwitNewsCor is a comprehensive dataset for understanding the content production, dissemination, and audience engagement dynamics of online local media in the UK. It comprises over 2.5 million online news articles from 360 local outlets, collected from 2020 to 2022. The corpus represents all articles shared from the X (then Twitter) accounts of these outlets and were sourced from over 4.7 million tweets from these accounts during the same period. We provide social media performance metrics for the articles and further augment the dataset by adding metadata on content duplication across domains and information about the geographic coverage targeted by each domain. We supplement the article dataset with directories of domains, of district, and of publishers, within which we supply statistics about the coverage extent of UKTwitNewsCor respective to the online local media sector in the UK at the time of data collection (January 2023) to facilitate quick analyses of the local media ecosystem as well as purposive sampling of the articles.

A paper associated with the dataset is published at: https://doi.org/10.1017/chr.2025.10012The Local Media UK Geoparsing (LMUK-Geo) dataset is a collection of 182 news articles sourced from local media outlets in the United Kingdom, designed for the task of geoparsing and location-based analysis. The articles have been tagged and resolved by two annotators, providing geographic references such as locations, facilities, and geopolitical entities. This dataset is intended to support research in media studies, geoparsing, and the geographic analysis of news content, with a particular focus on local journalism in the UK. Each row in the dataset corresponds to a toponym mention, and it is complete with coordinates and Local Authority District within which the coordinates are situated, start and end position, toponym type, domain, publisher, and coverage district of the publisher. Key Features: - Annotated geographic entities (GPE, LOC, FAC) - Articles sourced from UK-based local news outlets - Manual annotations with geographic coordinates and Local Authority District references Intended Use: This dataset is suitable for research in geoparsing, local media studies, content analysis, and natural language processing (NLP), particularly in the context of location reference identification and disambiguation. It provides a foundation for studying the geographic distribution of news content, media representation of places, and the evolving relationship between local journalism and geographic context.

This is replication data for "Mapping News Geography: A Computational Framework for Classifying Local Media Through Geographic Coverage Patterns". Instructions for usage and code can be found at the following GitHub repository: https://github.com/simonabisiani/geographic-local-media-classifier

In the last decade, data journalism has established itself as a thriving field. Recently, COVID-19 has boosted the demand for data-driven reporting to make sense of the pandemic, increasing the importance of studying the evolution of this rapidly evolving and technology-bounded practice. However, the number of efforts to map and systematically measure the data journalism industry are few. This paper analyses the findings of The State of the Data Journalism Survey 2021, currently the most extensive study on the characteristics surrounding the workforce producing and contributing to the data journalism industry. The outcome is an understanding of an expanding workforce with a geographically uneven distribution, which is still homogeneous in terms of tools and educational paths. Self-taught, resourceful, and multi-skilled, data journalists often work in isolation but share pressures of limited resources, time limitations, and access to quality data. The pandemic appears to have directly increased those struggles, although data journalists agree that the field's reputation has ultimately benefited from it.

This dataset contains several spreadsheets within which four public datasets of print and digital local news outlets in the UK (JICREG, ABC, PINF, and MRC) are triangulated and combined. In addition, the observations from these four datasets have been manually verified to flag obsolete observations. This helped generate a novel, powerful list of print and digital local news outlets (this can be found in sheet "Stage 2 - clean df with enhancements" and includes any observations marked as 1 under the "Baseline" column). The script where manipulation of these datasets occur can be found here: https://github.com/simonabisiani/Local-News-Datasets-Triangulation. The dataset was used to carry out research which resulted in the following journal article: https://www.mdpi.com/2673-5172/4/4/77.

Local journalism is fundamental for a thriving democracy, yet the UK faces a decline in the number of print and digital local news outlets. Large-scale mappings of the surviving outlets offer invaluable insights to policymakers designing interventions to strengthen the sector. Due to the lack of a comprehensive national directory of UK print and digital local news outlets, researchers have resorted to datasets such as circulation auditors’ databases, which have been noted to be incomplete and outdated. A lack of understanding of the magnitude of these data limitations hinders researchers from selecting optimal datasets. This study evaluates four commonly used local news databases, uncovering significant variations in their currentness and comprehensiveness. Thereafter, statistical analyses demonstrate the significant effect of each dataset’s shortcomings on findings in local news research. To address this issue, triangulation and manual verification are employed to create a more comprehensive and robust dataset. This procedure generates a new national dataset of print and digital local news outlets that can be used in future research, alongside a framework for leveraging public data to build an independent research dataset. This work paves the way for more rigorous research in data-driven local news provision studies. Concluding remarks stress the importance of setting definitions and establishing clear data pipelines in an increasingly diversified and dynamic sector.