Replication Data: "SNAP Judgments into the Digital Age: Reporting on Food Stamps Varies Significantly with Time, Publication Type, and Political Leaning"

This is the replication dataset for the publication "SNAP Judgments into the Digital Age: Reporting on Food Stamps Varies Significantly with Time, Publication Type, and Political Leaning." We used machine learning techniques to characterize media coverage of SNAP over time (1990-2017), between outlets with national readership and those with narrower scopes, and, for a subset of web-based media, by the outlet’s political leaning. We applied structural topic models, a machine learning methodology that categorizes and summarizes large bodies of text that have document-level covariates or metadata, to a corpus of print media (the "Print Corpus") retrieved via LexisNexis (n=76,634). For comparison, we complied a separate corpus (the "Online Corpus") via web-scrape algorithm of the Google News API (2012-2017), and assigned political alignment metadata to a subset documents according to a recent study of partisanship on social media (Bakshy E, Messing S, Adamic L. Replication Data for: Exposure to Ideologically Diverse News and Opinion on Facebook. Harvard Dataverse, V2; 2015. Available: doi:10.7910/DVN/LDJ7MS). A similar procedure was used on a subset of the print media documents(the "Print Subset Corpus") that could be matched to the same alignment index. This replication dataset provides all supplemental files related to the publication, including he full Online Corpus and appended metadata are available, and a minimal anonymized dataset for the Print/Print Subset corpora where full document texts are replaced with document headings but with all metadata intact