Automatic extraction of learning concepts from exam query repositories
Abstract
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 exam query repositories, which are commonly pre-dating modern e-learning systems. Exam queries in those repositories usually lack additional metadata which helps establish relationships between questions and corresponding learning concepts whose adoption is being tested. In this paper we present our novel approach of using data mining methods able to automatically annotate pre-existing exam queries with information about learning concepts they relate to, leveraging both textual and visual information contained in the queries. This enables automatic categorization of exam queries which allows for both better insight into the usability of the current exam query corpus as well as easier reporting of learning concept adoption after these queries are used in exams. 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.
Keywords
educational data mining, exam queries, learning concepts, classification, e-learning
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
D. Pintar, D. Begušić, F. Škopljanac-Mačina and M. Vranić, "Automatic extraction of learning concepts from exam query repositories," in Journal of Communications Software and Systems, vol. 14, no. 4, pp. 312-319, October 2018, doi: 10.24138/jcomss.v14i4.605
@article{pintar2018automaticextraction,
author = {Damir Pintar and Domagoj Begušić and Frano Škopljanac-Mačina and Mihaela Vranić},
title = {Automatic extraction of learning concepts from exam query repositories},
journal = {Journal of Communications Software and Systems},
month = {10},
year = {2018},
volume = {14},
number = {4},
pages = {312--319},
doi = {10.24138/jcomss.v14i4.605},
url = {https://doi.org/10.24138/jcomss.v14i4.605}
}