In order to be able to reproduce GneissWeb, we provide here GneissWeb.Edu_classifier - an education category fastText classifier. This fastText model is used as part of the ensemble filter in GneissWeb to detect documents with education content.
The model is trained on 800k documents, labeled using the
WatsonNLP hierachical categorization. Please refer to
fastText text classification tutorial for details.
Training data is selected as follows:
