Application of Data Mining Techniques in Determining the 
Accuracy of the Models Predicting the Student 
Academic failure

Fadavi, Azadeh; Salehi, Keyvan; Khodaie, Ebrahim; Moghadamzadeh, Ali; Javadipour, Mohammad

doi:10.29252/sjimu.28.1.36

[Home ] [Archive]

[ فارسی ]

Journal of Ilam University of Medical Sciences

Main Menu

Home

Journal Information

Articles archive

Publication Ethics

Peer Review Process

Indexing Databases

For Authors

For Reviewers

Subscription

Contact us

Site Facilities

Google Scholar Metrics

	All	Since 2019
Citations	6781	4025
h-index	27	21
i10-index	202	97

Search in website

Receive site information

Registered in

Volume 28, Issue 1 (3-2020)

Journal of Ilam University of Medical Sciences 2020, 28(1): 36-46

Back to browse issues page

Application of Data Mining Techniques in Determining the Accuracy of the Models Predicting the Student Academic failure

Azadeh Fadavi¹

, Keyvan Salehi ^*

², Ebrahim Khodaie¹

, Ali Moghadamzadeh¹

, Mohammad Javadipour¹

1- Dept of Curriculum Planning, Faculty of Education and Psychology, University of Tehran, Tehran, Iran
2- Dept of Curriculum Planning, Faculty of Education and Psychology, University of Tehran, Tehran, Iran , keyvansalehi@ut.ac.ir

Abstract: (3321 Views)

Introduction: Student academic failure is one of the shortcomings of higher education system. A system with the ability to predict and prevent the academic failure can play a decisive role in enhancing the quality of education. The utilization of educational data mining is one of the most effective strategies in monitoring and improving the quality of education. This study aimed to compare different data mining techniques in order to determine the best prediction model.

Materials & Methods: The study population consists of all undergraduate students studying Medical Laboratory Sciences, Health Information Technology Management, and Radiation Sciences Technology in Tehran University of Medical Sciences, Tehran, Iran in the academic year of 2018-2019. In total, 500 were selected to participate in this study. After administering and excluding the invalid questionnaires, 153, 85, and 73 questionnaires from the students of Medical Laboratory Sciences, Health Information Technology Management, and Radiation Sciences Technology were analyzed, respectively. The data were collected using students' academic failure questionnaire with a reliability Cronbach's alpha coefficient of 0.971 and confirmed content validity by experts. Furthermore, the data were analyzed in SPSS (version 16), SmartPLS 3, and SPSS-Modeler (Clementine) (version 18) software through logistic regression, decision tree, neural network, Bayesian network, and the support vector machine algorithms. Ethics code: IR.UT.PSYEDU.REC.1398.024

Findings: The results showed a significant difference among the majors in terms of the level of academic failure (P=0.046). Regarding the Medical Laboratory Sciences, the descending order of the accuracy of the data prediction model using each algorithm includes decision tree and Bayesian network, support vector machine, neural network, and logistic regression. In addition, considering the Health Information Technology Management and Radiation Sciences Technology, the best prediction models were Bayesian Network, Support Vector Machine, Neural Network, and logistic regression in a descending order. It is worth mentioning that the decision tree algorithm had no answer. Furthermore, the Chi-square test showed a statistically significant difference among the students of Medical Laboratory Sciences (0.88), Health Information Technology Management (0.001), and Radiation Science Technology (0.000) regarding the obtained algorithms.

Discussion & Conclusions: The results indicated that the logistic regression model had less predictive power in real data, compared to the network models. Therefore, the appropriate data prediction algorithm must be explored in any dataset. Predictive algorithms are well capable to predict academic failure in all three majors at the departments of allied medical sciences. Moreover, it can be used for medical and allied medical science students to identify students at the risk of failing to take preventive measures.

Keywords: Academic performance, Academic failure, Data mining, Educational data mining

Full-Text [PDF 715 kb] (856 Downloads)

Type of Study: Research | Subject: stats
Received: 2019/08/27 | Accepted: 2019/12/8 | Published: 2020/03/29

References

1. Vanklaveren C, Kooiman K, Cornelisz, I, Meeter M. [The higher education enrollment decision: feedback on expected study success and updating behavior]. J Res Edu Eff 2019; 12: 1-23. doi. 10.1080/19345747.2018.1496501

2. Vahabi A, Khatrei A, Vahabi B, Mirzaee M, Ahmadian M. [The perspective of public health students of Kurdistan University of medical sciences regarding field of study and future career and its related factors in 2014]. J Nurs Mid Pramed 2016; 1: 33-45. (Persian) doi. 10.29252/sjnmp.1.3.5

3. Emamghorashi F, Heydari ST, Najafipour S.[ Evaluation of effecting factors on educational status of medical students in Jahrom Medical University during 1994- 2003]. JBUMS 2010; 12: 40-45. (Persian)

4. Atashnafas M, Atashnafas E. [GIS and Irans holistic scientific map on health domain]. HBIJ 2011; 8: 305-313. (Persian)

5. Ehsanpour S. [Achieving minimum learning requirements from the viewpoints of midwifery students in Isfahan school of nursing and midwifery]. Iranian J Med Edu2006; 6:17-25. (Persian)

6. Banik P, Kumar B. [Impact of information literacy skill on students academic performance in Bangladesh]. Int J European Stud 2019; 3: 27-33. doi. 10.11648/j.ijes.20190301.15

7. Widyastuti T, Kurniawan A, Chandra NP. [Coping strategies on students after experiencing academic failure an indigenous study in javanese context]. Work Pap Ser 2017; 3:22-6.

8. Motlagh M, Elhampour H, Shakurnia A. [Factors affecting students' academic failure in Ahvaz Jundishapur University of medical sciences in 2005]. Iran J Med Edu 2008; 8: 91-9.

9. Aremu A, Sokan B. [A multi causal evaluation of academic performance of Nigerian learners issues and implications for national development]. Dep Guid Coun Uni Ibadan 2003;2:124-9.

10. Shams B, Farshidfar M, Hassanzadeh A. [Effect of counseling on the achievement of university students with dropout]. Iranian J Med Edu 2000; 1: 36-41.

11. Jabraili M, Mousavivaezi SJ, Mikaeli P, Saadatyanov R, Aqlmad S. [Evaluating the influencing factors of educational underachievement in gifted and talented students of Urmia University of medical sciences]. Horiz Med Edu Dev 2011; 4: 21-5.

12. Moniri R, Ghalebtarash H, Mussavi G. [The reasons of educational failure among paramedical students in Kashan University of Medical Sciences]. Iranian J Med Edu 2006; 1: 13540. (Persian)

13. Lancia L, Petrucci C, Giorgi F, Dante A, Cifone MG. [Academic success or failure in nursing students, results of a retrospective observational study]. Nurs Edu Today 2013; 33: 1501-5. doi:10.1016/j.nedt.2013.05.001

14. Rafoth MA. Academic failure prevention of encyclopedia of applied psychology. 1th ed. Spielberger CD Acad Publication. 2004; P. 1-7

15. Ashraf A, Anwer S, Khan MK. [A comparative study of predicting student performance by use of data mining techniques]. ASRJETS 2018; 44: 122-36.

16. Baker RSJD. [Data mining for education]. Int Enc Edu 2010; 7: 112-18. doi.org/10.1016/B978-0-08-044894-7.01318-X

17. Baker RS, Yacef K. [The state of educational data mining in 2009: A review and future visions]. J Edu Data Min 2009; 1: 3-17. doi.org/10.5281/zenodo.3554657

18. Delavari N. Beikzadeh MR. [A new analysis model for data mining processes in higher educational systems]. Int Sym Inf Com Tech Malaysia 2004;2:23-8.

19. Kabakchieva D. [Predicting student performance by using data mining methods for classification]. Cyb Inf Tech 2013; 13: 61-72. doi. 10.2478/cait-2013-0006

20. Luan J. Data Mining and knowledge management in higher education potential applications. Pres AIR Canada2002; 4:218-23.doi.org/10.1002/ir.35

21. Antonogeorgos G, Panagiotakos DB, Priftis KN, Tzonou A. [Logistic regression and linear discriminant analyses in evaluating factors associated with asthma prevalence among 10- to 12-years-old children: divergence and similarity of the two statistical methods]. Int J Pediatr2009; 3:952042. doi. 10.1155/2009/952042

22. Larose DT. Discovering knowledge in data an introduction to data mining. John Wiley Son Inc Publication 2005;P.142-7. doi. 10.1002/0471687545

23. Collins GS, Mallett S, Omar O. [Developing risk prediction models for type 2 diabetes a systematic review of methodology and reporting]. BMC Med2011; 5:146-59. doi.org/10.1186/1741-7015-9-103

24. Millan E, Loboda T, Perez JL. [Bayesian networks for student model engineering]. Comp Edu 2010; 55:1663-83. doi. 10.1016/j.compedu.2010.07.010

25. Hamedi A, Dirin A. [A bayesian approach in students’ performance analysis]. 10th Int Con Edu New Learn Technol 2018; Spain. doi. 10.21125/edulearn.2018.2498

26. Bellotti T. Crook J. [Support vector machines for credit scoring and discovery of significant features]. Exp Sys Appl 2009; 36: 3302-30. doi. 10.1016/j.eswa.2008.01.005

27. Willcockson IU, Johnson CW, Hersh W, Bernstam EV. Predictors of student success in graduate biomedical informatics training introductory course and program success. J Am Med Inf Ass 2009;16: 837-46. doi. 10.1197/jamia.M2895

28. Shannaq B, Rafael Y, Alexandro V.[Student relationship in higher education using data mining techniques]. Glob J Comp Sci Technol2010; 10: 54-9.

29. Eskandari M, rostami A, Hojati A, Kolifarhood G. [Trends of academic failure and its demographic determinants among medical students in Zanjan University of medical sciences]. Iranian J Med Edu 2014; 14:174-83.

30. Asif R, Merceron A, Ali S, Haider N. [Analyzing undergraduate student performance using educational data mining]. Comp Edu 2017; 113: 177-94. doi.org/10.1016/j.compedu.2017.05.007

31. Motlagh, M., Elhampour, H. Shakurnia A. [Factors affecting student academic failure in Ahvaz Jundishapur University of medical sciences in 2005]. Iran J Med Edu 2008; 8: 91-9.

32. Fadavi roodsari A, Salehi K, Khodaii E, Mogadamzadeh A, Javadipoor M. [Factors associated with bachelor student academic failure in University of Tehran]. Iran J Med Edu2016;2:72-7.

33. Tagharrobi Z, Fakharian E, Mirhoseini F, Rasooli Nejad SA, Akbari H, Ameli H. [Survey of educational drop-out indexes and realate factor in alumni of paramedical faculty of Kashan University of Medical Sciences]. J Babol Uni Med Sci 2010; 12 :76-89.

34. Edalatkhah H, Jahangiri S, Khanbabazadeh M, Amani F, Hashimilir M. [The educational situation of graduates in Ardebil University of Medical Sciences]. IJME 2005; 5: 193-5.

35. Chaware A. [Educational data mining an emerging trends in education]. Int J Adv Res Comp Sci 2011; 2: 117-22.

36. Sudhakar K, Manimekalai DM. [Study of heart disease prediction using data mining]. J Adv Res Comp Sci Soft Eng 2014; 4: 1157-60.

37.

Send email to the article author

Add your comments about this article

‎ 10.29252/sjimu.28.1.36

Mendeley

Zotero

RefWorks

Fadavi A, Salehi K, Khodaie E, Moghadamzadeh A, Javadipour M. Application of Data Mining Techniques in Determining the Accuracy of the Models Predicting the Student Academic failure. J. Ilam Uni. Med. Sci. 2020; 28 (1) :36-46
URL: http://sjimu.medilam.ac.ir/article-1-5954-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 28, Issue 1 (3-2020)

Back to browse issues page

Persian site map - English site map - Created in 0.15 seconds with 41 queries by YEKTAWEB 4666