Binary Field of Research Classification Data

The zip file includes the following data: Class category list (for categorical baseline), Document text: containing the title + abstract of each dataset instance. Class ORKG texts only: containing the dataset's ORKG label for each instance. Class DBpedia texts only: containing texts extracted from the linked DBpedia entity for each instance (the text is derived from rdfs:label + rdfs:comment) Class KGEs: containing DBpedia entity embeddings for each instance. The embeddings are pre-trained and extracted from https://zenodo.org/records/6384728. Author embedding per instance. Publisher embedding per instance. Labels: containing binary labels indicating whether an instance is a positive or negative sample.