Main content
When labeling L2 users as nativelike or not, consider classification errors
Date created: 2018-02-15 11:39 AM | Last Updated: 2018-12-03 09:56 AM
Category: Project
Description: Data and code for "When labeling L2 users as nativelike or not, consider classification errors"
illustration_randomforest.csv
: Dataset used to illustrate the use of random forests. Used to draw Figures 3, 4 and 5. Cleaned version of the data provided by Vanhove & Berthele (2017), Testing the interdependence of languages (HELASCOT project). doi:10.21832/BERTHE9047.
nativelikeness_4dist.csv
: Miss rates for nativelikeness studies with a single task. Used to draw Figure 1.
nativelikeness_all.csv
…