Update README.md

README.md

@@ -24,7 +24,7 @@ With this model, you can classify emotions in English text data. The model was t
 6) sadness
 7) surprise
 
-The model is a fine-tuned checkpoint of DistilRoBERTa-base.
+The model is a fine-tuned checkpoint of DistilRoBERTa-base. The emotions reflect Ekman's 6 universal emotions, plus a neutral class.
 
 ## Application
 
@@ -44,7 +44,7 @@ Thanks to Samuel Domdey and chrsiebert for their support in making this model av
 
 ## Appendix
 
-Please find an overview of the datasets used for training below. The table summarizes which emotions are available in each of the datasets.
+Please find an overview of the datasets used for training below. All datasets contain English text. The table summarizes which emotions are available in each of the datasets.
 
 |Name|anger|disgust|fear|joy|neutral|sadness|surprise|
 |---|---|---|---|---|---|---|---|
@@ -53,4 +53,4 @@ Please find an overview of the datasets used for training below. The table summa
 |GoEmotions, Demszky et al. (2020)|Yes|Yes|Yes|Yes|Yes|Yes|Yes|
 |ISEAR, Vikash (2018)|Yes|Yes|Yes|Yes|-|Yes|-|
 |MELD, Poria et al. (2019)|Yes|Yes|Yes|Yes|Yes|Yes|Yes|
-|SemEval-18|Yes|-|Yes|Yes|-|Yes|-|
+|SemEval-2018, EI-reg (Mohammad et al. 2018) |Yes|-|Yes|Yes|-|Yes|-|