Figure 2.

Braindr rating aggregation and citizen scientist importance. (A) ROC curves on the test set for various training set sizes (here n denotes the number of training slices used). The dashed line is the ROC curve of the average citizen scientist ratings for all slices. (B) The distribution of XGBoost probability scores on all Braindr slices. (C) Feature importance for each anonymized user. (D) Relationship between citizen scientist importance and total number of ratings in the gold-standard dataset.