Evaluation of Concept Importance in Concept Maps Mined from Lecture Notes - Computer Vs Human

Thushari Atapattu, Katrina Falkner, Nickolas Falkner


Concept maps are commonly used tools for organising and representing knowledge in order to assist meaningful learning. Although the process of constructing concept maps improves learners’ cognitive structures, novice students typically need substantial assistance from experts. Alternatively, expert-constructed maps may be given to students, which increase the workload of academics. To overcome this issue, automated concept map extraction has been introduced. One of the key limitations is the lack of an evaluation framework to measure the quality of machine-extracted concept maps. At present, researchers in this area utilise human experts’ judgement or expert-constructed maps as the gold standard to measure the relevancy of extracted knowledge components. However, in the educational context, particularly in course materials, the majority of knowledge presented is relevant to the learner, resulting in a large amount of information that has to be organised. Therefore, this paper introduces a machine-based approach which studies the relative importance of knowledge components and organises them hierarchically. We compare machine-extracted maps with human judgment, based on expert knowledge and perception. This paper describes three ranking models to organise domain concepts. The results show that the auto-generated map positively correlates with human judgment (rs~1) for well-structured courses with rich grammar (well-fitted contents).


  1. Atapattu, T, Falkner, K. and Falkner, N. 2012. Automated extraction of semantic concepts from semi-structured data: supporting computer-based education through analysis of lecture notes. In proceedings of the 23rd International conference on Database and Expert systems applications, Vienna, Austria.
  2. Alves, A., Pereira, F and Cardoso, F. 2002. Automatic reading and learning from text. In International Symposium on Artificial Intelligence.
  3. Ausubel, D., Novak, J. and Hanesian, H. 1978. Educational psychology: A cognitive view, New York.
  4. Chang, S. N. 2007. Externalising students' mental models through concept maps. Journal of Biological Education.
  5. Chen, N., Kinshuk, and Wei, C. 2008. Mining e-learning domain concept map from academic articles, Computer and Education.
  6. Coffey, J., Carnot, M., Feltovich, P., Feltovich, J., Hoffman, R., Canas, A. and Novak, J. 2003. A summary of literature pertaining to the use of concept mapping techniques and technologies for education and performance support, The Chief of Naval Education and Training.
  7. Dali, L., Rusu, D., Fortuna, B., Mladenic, D., Grobelnik, M. 2009. Question answering based on Semantic graphs. In Language and Technology Conference. Poznan, Poland.
  8. Frantzi, K., Ananiadou, S. and Mima, H. 2000. Automatic recognition of multi-word terms: the C-value/NCvalue method. International Journal on Digital Libraries.
  9. Gantayat, N and Iyer, S. 2011. Automated building of domain ontologies from lecture notes in courseware. In Proceedings of the IEEE international conference on Technology for education, India.
  10. Gouli, E., Gogoulou, A., Papanikolaou, K. and Grigoriadou, M. 2004. COMPASS: An adaptive webbased concept map assessment tool. In Proceedings of the first international conference on concept mapping.
  11. Hearst, M. A., 2000. The debate on automated essay grading. Intelligent systems and their Applications.
  12. Kinchin, I. 2006. Developing PowerPoint handouts to support meaningful learning. British Journal of Education technology. 37 (4), 647-650.
  13. Leake, D., Maguitman, A. and Reichherzer, T. 2004. Understanding Knowledge Models: Modelling Assessment of Concept Importance in Concept Maps. In Proceedings of CogSc.
  14. Maass, J., Pavlik, P. 2013. Utilising Concept mapping in Intelligent Tutoring Systems. In Artificial Intelligence in Education.
  15. Novak, J. and Canas, A. 2006. The theory underlying Concept maps and How to construct and use them. Institute of Human and Machine Cognition.
  16. Novak, J. and Gowin, D. 1984. Learning how to learn. Cambridge University Press, New York and Cambridge.
  17. Olney, A. M., Graesser, A. and Person, N. 2012. Question generation from Concept maps. Special issue on Question generation, Dialogue and Discourse.
  18. Ono, M., Harada, F. and Shimakawa, H. 2011. Semantic network to formalise Learning items from Lecture notes. International Journal of Advanced Computer Science.
  19. Starr, R. and Oliveira, J. 2013. Concept maps as the first step in an ontology construction. Information systems.
  20. Villalon, J. and Calvo, R., 2008. Concept map mining: A definition and a framework for its evaluation. In International Conference on Web Intelligence and Intelligent Agent Technology.
  21. Zouaq, A. and Nkabou, R. 2009. Evaluating the generation of domain ontologies in the knowledge puzzle project. IEEE Transactions on Knowledge and Data Engineering.
  22. Zouaq, A., Gasevic, D. and Hatala, M. 2012. Voting theory for concept detection. The Semantic Web: Research and Applications.

Paper Citation

in Harvard Style

Atapattu T., Falkner K. and Falkner N. (2014). Evaluation of Concept Importance in Concept Maps Mined from Lecture Notes - Computer Vs Human . In Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU, ISBN 978-989-758-020-8, pages 75-84. DOI: 10.5220/0004842300750084

in Bibtex Style

author={Thushari Atapattu and Katrina Falkner and Nickolas Falkner},
title={Evaluation of Concept Importance in Concept Maps Mined from Lecture Notes - Computer Vs Human},
booktitle={Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU,},

in EndNote Style

JO - Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU,
TI - Evaluation of Concept Importance in Concept Maps Mined from Lecture Notes - Computer Vs Human
SN - 978-989-758-020-8
AU - Atapattu T.
AU - Falkner K.
AU - Falkner N.
PY - 2014
SP - 75
EP - 84
DO - 10.5220/0004842300750084