Replication data and results for the paper "Keyness in song lyrics. Challenges of highly clumpy data"

Abstract

Replication data and results for Langenhorst, Jan/Frommherz, Yannick/Meier-Vieracker, Simon: Keyness in song lyrics. Challenges of highly clumpy data. In: Journal for Language Technology and Computational Linguistics.

This data set contains * Python module used to obtain results presented in paper * Jupyter Notebooks to generate results and create plots * Complete keyword/key-ngram lists * A 'shuffled' version of the songkorpus used in our analysis (replication of ngrams not possible, only keywords)