Table 6.

The results of data diversification, where “train” and “test” respectively represent the number of samples in the training set and the testing set.

Dataset Label With data augmentation
Without data augmentation
Train Test Train Test
SST-2 Positive 17 300 911 3460 911
Negative 17 300 910 3460 910
Offensive 29 790 431 5958 431
OLID2 Not-Offensive 29 790 431 5958 431
AG News World 135 000 1900 27 000 1900
Sports 135 000 1900 27 000 1900
Business 135 000 1900 27 000 1900
Science 135 000 1900 27 000 1900

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.