This paper describes the results of a study designed to assess human expert ratings of educational concept features for use in automatic core concept extraction systems. Digital library resources provided the content base for human experts to annotate automatically extracted concepts on seven dimensions: coreness, local importance, topic, content, phrasing, structure, and function. The annotated concepts were used as training data to build a machine learning classifier as part of a tool used to predict the core concepts in the document. These predictions were compared with the experts' judgment of concept coreness.