Quality Assessment in Vocational Education Based on a Hierarchical Classification Technique

Abstract:

According to the laws of education in Thailand, the Office for National Education Standards and Quality Assessment is responsible for assessing the external educational institutes in order to develop the quality and educational standards. The external quality assessment reports are represented in both structured and unstructured data. In this paper, we focus on the analysis of unstructured data, i.e., to automatically classify strength and weakness points. We propose and evaluate two different classification models: Flat Classification and Hierarchical Classification. Three algorithms, Naive Bayes, Support Vector Machines (SVM) and Decision Tree, were used in the experiments. The results showed that classification viathe Hierarchical Classification model by using the SVM yielded the best performance. The classification of strength and weakness points yielded the F-measure equal to 0.843 and 0.893, respectively. The proposed approach can be applied as a decision support function for quality assessment in vocational education.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 3724-3728
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.3724
• Online since: November 2011
• Authors: Chantima Ekwong, Sageemas Na Wichain, Choochart Haruechaiyasak
• Keywords: Hierarchical Classification, Quality Assessment, Vocational Education

References

[1] C. Haruechaiyasak, W. Jitkrittum, C. Sangkeettrakarn and C. Damrongrat. Implementing News Article Category Browsing Based on Text Categorization Technique. Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference Volume 3, pages 143–146, (2008).

DOI: 10.1109/wiiat.2008.61

[2] L. Peng, Y. Gao and Y. Yang. Automatic text classification based on knowledge tree. Cybernetics and Intelligent Systems, 2008 IEEE Conference , pages 681–684, (2008).

DOI: 10.1109/iccis.2008.4670777

[3] G. Shi and Y. Kong. Advances in Theories and Applications of Text Mining. Information Science and Engineering (ICISE), 2009 1st International Conference, pages 4167–4170, (2009).

[4] M. Gao, J. Tian and S. Zhou. Research of web classification mining based on classify support vector machine. Computing, Communication, Control, and Management, CCCM 2009. ISECS International Colloquium, Volume: Digital Object, pages 21–24, (2009).

DOI: 10.1109/cccm.2009.5268004

[5] Office of the National Education Commission. National Education Act B.E. 2542 (1999) and Amendments (Second National Education Act B.E. 2545 (2002). Bangkok: Pimdeekarnpim Co., Ltd., pages 22-23, (2003).

[6] S. Yin, Z. Huang, L. Chen and Y. Qiu. A Approach for Text Classification Feature Dimensionality Reduction and Rule Generation on Rough Set. Innovative Computing Information and Control, ICICIC '08. 3rd International Conference, page 554, (2008).

DOI: 10.1109/icicic.2008.7

[7] The office for National Education Standards and Quality Assessment (Public Organization). Manual for External Quality Assessment to Certification of Vocational Education. Bangkok: 21 century Co., Ltd., pages 29-32, (2007).

[8] Z. Liu, X. Lv, K. Liu and S. Shi. Study on SVM Compared with the other Text Classification Methods. Education Technology and Computer Science (ETCS), 2010 Second International Workshop, Volume 1, pages 219–222, (2010).

DOI: 10.1109/etcs.2010.248