USING THE C4.5 ALGORITHM TO BUILD A DECISION TREE  FOR THE CAREER CHOICE PROBLEM OF HIGH SCHOOL STUDENTS  IN THAI NGUYEN PROVINCE

Bùi Ngọc Tuấn

doi:10.34238/tnu-jst.7590

USING THE C4.5 ALGORITHM TO BUILD A DECISION TREE FOR THE CAREER CHOICE PROBLEM OF HIGH SCHOOL STUDENTS IN THAI NGUYEN PROVINCE

About this article

Received: 22/03/23 Revised: 27/04/23 Published: 28/04/23

Authors

Bui Ngoc Tuan , TNU - University of Information and Communication Technology

Abstract

In this study, a decision tree was built and the career selection results of grade-12 students in Thai Nguyen province were predicted by algorithm C4.5. Research results have shown that this decision tree has high accuracy and is built based on data collection and preprocessing. However, it is found that the study can only be applied to Thai Nguyen province and needs to be optimized to give more accurate prediction results. Data was collected through a questionnaire of 900 grade-12 students at Ngo Quyen, Tran Quoc Tuan, and Dong Hy high schools in Thai Nguyen province. The author used primary factors to assess, including social needs, learning outcomes, family economic conditions, place of residence and gender. Research results showed that the social needs and learning ability were factors that have a great impact on students’ intention to choose a career. At the same time, the classification based on algorithm C4.5 was confirmed to bring higher classification accuracy than the technique based on the Bayes algorithm. This research can contribute to support the university admissions process as well as to help guide the careers of high school students, mainly in grade 12.

Keywords

High school students; Decision Tree; Algorithm C4.5; WEKA; J48

Full Text:

PDF (Tiếng Việt)

References

[1] T. H. Bui, “On the algorithms for constructing decision trees and reducing rule sets,” (in Vietnamese), Journal of Computer Science and Control, vol.18, no. 4, pp. 323-332, 2002.

[2] T. N. A. Nguyen, D. H. Tran, P. H. Le, “Applying the method of machine learning - decision tree in assessing the changes of mangrove forest in Dat Mui commune,” (in Vietnamese), Climate Change Science, vol. 20, p. 33, 12/2021.

[3] D. W. Chapman, "A model of student college choice," The Journal of Higher Education, vol. 52, no. 5, pp. 490-505, 1981.

[4] A. Cabrera, "Understanding the college-choice process," New directions for institutional research, vol. 107, pp. 5-22, 2000.

[5] V. Q. Tran, “Factors influencing high school students' decision to choose a university,” (in Vietnamese), Journal of Climate Change Science, vol.15, pp. 89-91, 2009.

[6] N. L. Luu, “Identifying factors affecting the decision to choose a university among Lac Hong University students,” (in Vietnamese), Scientific research project, 2010.

[7] M. H. Nguyen, “A study of factors affecting students' decision to choose Ho Chi Minh City Open University,” (in Vietnamese), Journal of Science, Ho Chi Minh City Open University, vol. 6, no.2, pp.107-116. 2011.

[8] J. Edmonds, "Factors influencing choice of college major: what really makes a difference?" M.A. Thesis, Rowan University, 2012.

[9] J. R. Quinlan, Programs for Machine Learning, Morgan Kaufmann Publishers, Inc., 1993.

[10] I. H. Witten, “Data mining in bioinformatics using Weka,” Bioinformatics, vol. 20, no. 15, pp. 2479–2481, 2004.

[11] S. R. A. Fisher, "The Use of Multiple Measurements in Taxonomic Problems," Annals of Eugenics, vol.5, no.4, pp. 179-188, 1936.

DOI: https://doi.org/10.34238/tnu-jst.7590

Refbacks

There are currently no refbacks.



Remember me