Datasets used in this work and their main characteristics.

Columns LTr, LVa, U contain the numbers of tweets in the training set, held-out validation set, and test set, respectively. Column “Shift” contains the values of distribution shift between L ≡ LTr ⋃ LVa and U, measured in terms of absolute error, columns pL(⊕), pL(⊙), and pL(⊖) contain the class prevalence values of our three classes of interest in the training set L, while columns pU(⊕), pU(⊙), and pU(⊖) contain the class prevalence values for the unlabelled set U.