Structural Topic Models of water-quality related news articles and scientific abstracts in the Illinois River Basin, USA
This data release provides the input and output files, metadata,
and R scripts used to apply a Structural Topic Model (STM) to public (local news
articles) and scientific (abstracts) discourse on water quality in the Illinois
River Basin (ILRB). A total of 6,822 local news articles published from 2018 through
2022, and 190 scientific abstracts published from 2018 through 2023 were compiled
for use in a Structural Topic Model (STM), a statistical text-mining approach that
identified latent themes within a collection of documents while incorporating
document-level metadata to explain topic prevalence. The model inputs included
the text of each news article and scientific abstract along with associated
metadata (e.g., author, title, date, publisher, location of the news publisher;
citation information for scientific abstracts). Due to proprietary restrictions,
the full text of the local news articles (NewsArticles.xlsx) is not included in
this data release. Instead, we provide the scientific abstracts input file
(SCOPUS_scientificAbstracts.csv), the R scripts used to generate the STM analysis
for both the news articles (STM_newsArticles.R) and scientific abstracts
(STM_scientificAbstracts.R), and the corresponding model output showing the main
topics (STM_newsArticles_output.png and STM_scientificAbstracts_output.png).
This data release supports the analyses presented in the corresponding journal
article (https://www.doi.org/TBD). STM_newsArticles_output.png and
STM_scientificAbstracts_output.png correspond to Figures 3 and 9 in this article.
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[ "010:12" ] |
| contactPoint |
{ "fn": "Center Director, Upper Midwest Water Science Center", "@type": "vcard:Contact", "hasEmail": "mailto:gs-w-umidwsc_center_director@usgs.gov" } |
| description | This data release provides the input and output files, metadata, and R scripts used to apply a Structural Topic Model (STM) to public (local news articles) and scientific (abstracts) discourse on water quality in the Illinois River Basin (ILRB). A total of 6,822 local news articles published from 2018 through 2022, and 190 scientific abstracts published from 2018 through 2023 were compiled for use in a Structural Topic Model (STM), a statistical text-mining approach that identified latent themes within a collection of documents while incorporating document-level metadata to explain topic prevalence. The model inputs included the text of each news article and scientific abstract along with associated metadata (e.g., author, title, date, publisher, location of the news publisher; citation information for scientific abstracts). Due to proprietary restrictions, the full text of the local news articles (NewsArticles.xlsx) is not included in this data release. Instead, we provide the scientific abstracts input file (SCOPUS_scientificAbstracts.csv), the R scripts used to generate the STM analysis for both the news articles (STM_newsArticles.R) and scientific abstracts (STM_scientificAbstracts.R), and the corresponding model output showing the main topics (STM_newsArticles_output.png and STM_scientificAbstracts_output.png). This data release supports the analyses presented in the corresponding journal article (https://www.doi.org/TBD). STM_newsArticles_output.png and STM_scientificAbstracts_output.png correspond to Figures 3 and 9 in this article. |
| distribution |
[ { "@type": "dcat:Distribution", "title": "Digital Data", "format": "XML", "accessURL": "https://doi.org/10.5066/P1JZFCVA", "mediaType": "application/http", "description": "Landing page for access to the data" }, { "@type": "dcat:Distribution", "title": "Original Metadata", "format": "XML", "mediaType": "text/xml", "description": "The metadata original format", "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.67cefe98d34ecfe34cc866d5.xml" } ] |
| identifier | http://datainventory.doi.gov/id/dataset/USGS_67cefe98d34ecfe34cc866d5 |
| keyword |
[ "Illinois", "Illinois River Basin", "Indiana", "Structural Topic Model", "USGS:67cefe98d34ecfe34cc866d5", "Wisconsin", "groundwater quality", "surface water quality", "water quality" ] |
| modified | 2025-09-30T00:00:00Z |
| publisher |
{ "name": "U.S. Geological Survey", "@type": "org:Organization" } |
| spatial | -91.0547, 38.3761, -86.8799, 43.4529 |
| theme |
[ "geospatial" ] |
| title | Structural Topic Models of water-quality related news articles and scientific abstracts in the Illinois River Basin, USA |
