Annotating Exam Questions Through Automatic Learning Concept Classification

Educational data mining(or EDM) is an emerging interdisciplinary research field concerned with developing methods for exploring the specific and diverse data encountered in the field of education. One of the most valuable data sources in the educational domain are repositories of exam queries, which are usually designed for evaluating how efficient the learning process was in transferring knowledge about certain taught concepts, but which commonly do not contain any additional information about concepts they are related to beyond the text of the query and offered answers. In this paper we present our novel approach of using text mining methods to automatically annotate pre-existing exam queries with information about concepts they relate to. This enables automatic categorization of exam queries as well as easier reporting of learning concept adoption after these queries are used in an exam. We apply this approach to real-life exam questions from a high education university course and show validation of our results performed in consultation with experts from the educational domain.