guydepauw commited on
Commit
6c729af
1 Parent(s): e3e36fe

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Hate Speech Classifier for Social Media Content in Dutch
2
+
3
+ A monolingual model for hate speech classification of social media content in Dutch. The model was trained on 20000 social media posts (youtube, twitter, facebook) and tested on an independent test set of 2000 posts. It is based on thepre-trained language model [BERTje](https://huggingface.co/wietsedv/bert-base-dutch-cased).
4
+
5
+ ## Tokenizer
6
+
7
+ During training the text was preprocessed using the BERTje tokenizer. We suggest the same tokenizer is used for inference.
8
+
9
+ ## Model output
10
+
11
+ The model classifies each input into one of four distinct classes:
12
+ * 0 - acceptable
13
+ * 1 - inappropriate
14
+ * 2 - offensive
15
+ * 3 - violent