DALC
2022-09-09
A few Dutch students took the effort of making an Abusive Language Corpus for the Dutch language. They described their effort in a paper and also released the dataset on GitHub.
The repository also contains the GROF lexicon,
which comes with a lemma list that can be compared against.
Lists like these aren't perfect, but they can be a great starting point to detect abusive speech online. Many (Dutch) platforms can really benefit from that.