Replication Data for: Coding topics and frames in Dutch newspaper coverage (1995-2010)

Contributors
Publication date 2020
Description This file includes the raw data for the coding of Dutch newspaper coverage on topics (CAP majors topics) and frames - funded by a 'VENI' grant from the Dutch science foundation. Next to metadata, variables as mentioned in the codebook, the last three variables include the following: text (text split into words and randomly shuffled), text_bigrams (same thing but as bigrams) and text_bigrams_nostopwords (same thing but making bigrams after removing the stopwords using the Python nltk library)
Publisher Harvard Dataverse
Organisations
  • Faculty of Social and Behavioural Sciences (FMG) - Amsterdam School of Communication Research (ASCoR)
Document type Dataset
Related publication Teaching the computer to code frames in news: comparing two supervised machine learning approaches to frame analysis Using supervised machine learning to code policy issues: Can classifiers generalize across contexts?
DOI https://doi.org/10.7910/dvn/cpuprr
Other links https://doi.org/10.7910%2Fdvn%2Fcpuprr
Permalink to this page
Back