نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه مهندسی صنایع ، دانشکده مهندسی، دانشگاه تربت حیدریه، تربت حیدریه، ایران.

2 گروه مهندسی صنایع، دانشکده مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران.

10.22105/dmor.2021.239599.1182

چکیده

بررسی عملکرد تحصیلی دانشجویان با استفاده از داده‌کاوی آموزشی یکی از مهم‌ترین موضوعات در حوزه مدیریت آموزشی است و مورد توجه بسیاری از پژوهشگران قرار گرفته‌است. هدف پژوهش حاضر، ارائه روش تجربی برای انتخاب الگوریتم با بهترین عملکرد از منظر شاخص‌های ارزیابی در پیش‌بینی وضعیت تحصیلی دانشجویان در حالت دو و سه کلاسه است. پایگاه داده دوکلاسه، پذیرش یا رد دانشجویان در درس موردنظر را پیش‌بینی می‌کند، درحالی‌که پایگاه داده سه کلاسه، علاوه بر پذیرش یا رد به شناسایی دانشجویان مستعد و نخبه می‌پردازد. با استفاده از مقالات پیشین در حوزه داده‌کاوی آموزشی و نظرات خبرگان، فاکتورهای تاثیرگذار بر عملکرد تحصیلی دانشجویان شناسایی و براساس آن‌ها پایگاه داده تدوین شد. پس از تنظیم پارامترها و اجرای الگوریتم‌های مختلف، نمره عملکرد الگوریتم‌ها با استفاده از آزمون تی زوجی براساس سه شاخص صحت، F-measureو ROC  محاسبه شده، سپس با استفاده از روش‌های تاپسیس و ویکور، الگوریتم‌ها مقایسه و رتبه‌بندی شدند. در حالت دو کلاسه ماشین بردار پشتیبان در تاپسیس با مقدار 999115/0 ویکور با مقدار صفر بهترین عملکرد را از خود نشان داده ‌است. در حالت چندکلاسه، الگوریتم رگرسیون لجستیک در هر دو روش تاپسیس و ویکور با مقادیر به ترتیب 0.9986044 و 0.0009798، بهتر از سایر الگوریتم‌ها عمل کرده‌است. می‌توان روش پیشنهادی را به عنوان یک ابزار برای انتخاب الگوریتم با بهترین عملکرد در داده‌کاوی آموزشی استفاده نمود. زیرا انتخاب الگوریتم برای دستیابی به نتایج دقیق و صحیح بسیار موثر است و می‌توان در فرایند مشاوره و جلوگیری از افت تحصیلی دانشجویان با دقت نظر بیشتری عمل کرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Evaluation of data mining algorithms on educational data using multi-criteria decision-making methods

نویسندگان [English]

  • Fatemeh Mirsaeedi 1
  • hamidreza koosha 2
  • Mohammad Ghodoosi 1

1 Department of Industrial Engineering, Faculty of Engineering, University of Torbat Heydariyeh, Torbat Heydariyeh, Iran.

2 Department of Industrial Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.

چکیده [English]

Survey academic performance by educational data mining is one of the most important issues in the field of educational management and researchers focus on it. The purpose of this study is to present an experimental method for appropriate algorithm selection in predicting students' academic status in two and three classes. Two-class database predicts the admission or rejection of students in the course, while the database of the three classes, in addition to admission or rejection, identifies students who are prone and elite. Using the previous articles in the field of educational data mining and experts' opinions, factors that effect on academic performance of students were identified and database was compiled based on them. After optimization of parameters and implementation of different algorithms, the performance scores of the algorithms were calculated using paired t-test based on three indexes include of accuracy, f-measure, and ROC, algorithms were compared by TOPSIS and VIKOR methods. In the two-class mode, Support Vector Machine algorithm in TOPSIS with value of 0.999115 and VIKOR with value of zero has shown the best performance. In the multi-class mode, the Logistic Regression algorithm in TOPSIS and VIKOR in turns with values 0.9986044 and 0.0009798 performances better than other algorithms. The proposed method can be used as a tool for selecting algorithm that has the best pergormance in educational data mining. Because choosing the algorithm to achieve accurate and exact results is very effective and can be taken into account in the process of counseling and preventing students' academic failure

کلیدواژه‌ها [English]

  • Educational data mining
  • Comparison of algorithms
  • TOPSIS
  • VIKOR
Abdullah, Z., Herawan, T., Ahmad, N., & Deris, M. M. (2011). Mining significant association rules from educational data using critical relative support approach. Procedia-social and behavioral sciences28, 97-101.
Ahmadi, A., Karimzadgan, D., & Khairati Kazeroon, T. (2015). Data mining of students Withdrawal at University of Tehran, focusing on fee paid students (to prevent customer churn). Journal of information technology management, 7(2), 217-238. (In Persian).https://jitm.ut.ac.ir/article_53969.html
Alimohammadi, A. M., Abbasimehr, M. H., & Javaheri, A. (2016). Prediction of stock return using financial ratios: a decision Tree approach. Journal of financial management strategy, 3(4), 125-146. (In Persian).https://jfm.alzahra.ac.ir/article_2349.html?lang=en
Asgharizade, E., Ehsani, R., & Valipour Halabi, F. (2011). The performance appraisal of managers by using 360- degrees methods and VIKOR technique. Industrial management studies, 9(23), 21-48. (In Persian). https://www.sid.ir/en/journal/ViewPaper.aspx?ID=280066
Ashraf, M., Zaman, M., & Ahmed, M. (2020). An intelligent prediction system for educational data mining based on ensemble and filtering approaches. Procedia computer science167, 1471-1483.
Asif, R., Merceron, A., Ali, S. A., & Haider, N. G. (2017). Analyzing undergraduate students' performance using educational data mining. Computers & education113, 177-194.
Buldu, A., & Üçgün, K. (2010). Data mining application on students’ data. Procedia-social and behavioral sciences2(2), 5251-5259.
Chu, M. T., Shyu, J., Tzeng, G. H., & Khosla, R. (2007). Comparison among three analytical methods for knowledge communities’ group-decision analysis. Expert systems with applications33(4), 1011-1024.
Costa, E. B., Fonseca, B., Santana, M. A., de Araújo, F. F., & Rego, J. (2017). Evaluating the effectiveness of educational data mining techniques for early prediction of students' academic failure in introductory programming courses. Computers in human behavior73, 247-256.
Dypir, M., & Raboo, A. (2018). Using educational data mining for grouping learners in an E-Learning environment for customizing learning program. Journal of management and planning in educational systems, 11(1), 83-108.(In Persian). https://www.sid.ir/en/journal/ViewPaper.aspx?id=652872
ElGamal, A. F. (2013). An educational data mining model for predicting student performance in programming course. International journal of computer applications70(17), 22-28.
Fadavi Roodsari, A., Salehi, K., khodaie, E., Moghadamzadeh, A., & Javadipour, M. (2019). Bayesian network model of factors related to academic failure in Tehran university students. Sychological science, 18(76), 417-429. (In Persian). https://www.sid.ir/en/journal/ViewPaper.aspx?ID=689976
Fernandes, E., Holanda, M., Victorino, M., Borges, V., Carvalho, R., & Van Erven, G. (2019). Educational data mining: Predictive analysis of academic performance of public-school students in the capital of Brazil. Journal of business research94, 335-343.
Gunawan, A., & Lau, H. C. (2011). Fine-tuning algorithm parameters using the design of experiments approach. International conference on learning and intelligent optimization (pp. 278-292). Berlin, Heidelberg: Springer. https://doi.org/10.1007/978-3-642-25566-3_21
Hamsa, H., Indiradevi, S., & Kizhakkethottam, J. J. (2016). Student academic performance prediction model using decision tree and fuzzy genetic algorithm. Procedia technology25, 326-332.
Han, J., Kamber, M., & Pei, J.  (2012). Data Mining: concepts and techniques. USA: Morgan Kaufman.
Heydari, S., & Yaghini, M. (2011). Classification and prediction of students’ educational status using data mining techniques. Higher educaion letter, 12, 107-124. (In Persian). http://journal.sanjesh.org/article_15694.html?lang=en
Hutter, F., Hoos, H. H., Leyton-Brown, K., & Stützle, T. (2009). ParamILS: an automatic algorithm configuration framework. Journal of artificial intelligence research36, 267-306.
Izadi, S., & Mohammadzadeh Edmolaee, R. (2008). A study of relationship between learning styles, personality charac-teristics and academic performance. Daneshvar (Raftar) Shahed University, 14(27), 15-29. (In Persian). http://tlr.shahed.ac.ir/article_2182.html?lang=en
Janzadeh, A. (2011). Research and analysis in statistical community from all student's opinion assessment of the reasons in viewpoints of some student's departmental deputies of the universities. Iranian higher education, 3 (3), 137. (In Persian). http://ihej.ir/article-658-1-fa.html
Kabakchieva, D. (2013). Predicting student performance by using data mining methods for classification. Cybernetics and information technologies13(1), 61-72.
Kabakchieva, D., Stefanova, K., & Kismov, V. S. (2011). Analyzing university data for determining student profiles and predicting performance. Paper presented at the meeting of4th international conference on educational data mining, the Netherlands.
Kaur, P., Singh, M., & Josan, G. S. (2015). Classification and prediction-based data mining algorithms to predict slow learners in education sector. Procedia computer science, 57, 500-508.
Kheybari, S., & Kazemi, M. (2018). Extension of the TOPSIS considering the dispersion among the criteria of each alternative. Industrial management studies, 16(49), 199-219. (In Persian). https://www.sid.ir/en/journal/ViewPaper.aspx?id=606334
Koosha, H., Dangkoub, S., & Barzanooni, A. (2019). Application of data mining techniques to predict students' mental health status to improve educational performance. Technology of education journal, 13(1), 49-62. (In Persian). https://jte.sru.ac.ir/article_899.html?lang=en
Maghsoudi, B., Sulaimany, S., Amiri, A., & Afsharchi, M. (2013). Teaching quality improvement of electronic learning systems using educational data mining. Journal of technology of education, 6(4), 277-286. (In Persian). https://jte.sru.ac.ir/article_200.html?lang=en
Oskouei, R. J., & Askari, M. (2014). Predicting academic performance with applying data mining techniques (generalizing the results of two different case studies). Computer engineering and applications journal3(2), 79-88.
Pandey, M., & Taruna, S. (2016). Towards the integration of multipleclassifier pertaining to the student’sperformance prediction. Perspectives in science, 8, 364-366.
Rachburee, N., Punlumjeak, W., Rugtanom, S., Jaithavil, D., & Pracha, M.  (2018). A prediction of engineering students performance from core engineering course using classification. Computer science and engineering, 6(7), 43-48.
Romero, C., & Ventura, S. (2007). Educational data mining: a survey from 1995 to 2005. Expert systems with applications, 33, 135-146.
Rostami, M., Ayat, S,. Saghari, F., & Yaghoobi, F. (2015). Applying fuzzy clustering to assess and anticipate students' educational progress in learning environments. Journal of technology of education,10(1), 23-36. (In Persian). https://jte.sru.ac.ir/article_377_91.html?lang=en
Saa, A. A. (2016). Educational data mining & students’ performance prediction. International journal of advanced computer science and applications7(5), 212-220.
Sen, B., & Ucar, E. (2012). Evaluating the achievements of computer engineering department of distance education students with data mining methods. Procedia technology1, 262-267.
Sen, B., Ucar, E., & Delen, D.  (2012). Predicting and analyzing secondary education placement-test scores: a data mining approach. Expert systems with applications, 39, 9468-9476. 
Strecht, P., Cruz, L., Soares, C., & Mendes-Moreira, J. (2015). A comparative study of classification and regression algorithms for modelling students' academic performance. International educational data mining society, 8, 392-395.
Toloei Ashlaghi, A., Nikoomaram, H., & Maghdoori, F. (2010). Credit facilities applicant’s classification by SVM. Journal of future studies management, 21(84), 1-19. (In Persian). https://jmfr.srbiau.ac.ir/article_5077.html
Viana, R., Rodrigues, R. B., Alvarez, M., & Pistori. H. (2007). Svm with stochastic parameter selection for bovine leather defect classification. Advances in image and video technology, 4872, 600-612.
Xing, W., Guo, R., Petakovic, E., & Goggins, S. (2015). Participation-based student final performance prediction model through interpretable genetic programming: integrating learning analytics, educational data mining and theory. Computers in human behavior47, 168-181.
Yahya, A. A. (2019). Swarm intelligence-based approach for educational data classification. Journal of King Saud University-Computer and information sciences31(1), 35-51.
Yehuala, M. A. (2015). Application of data mining techniques for student success and failure prediction (The case of Debre_Markos University). International journal of scientific & technology research4(4), 91-94.
Zaefarian, T., Andabili, M., Momeni, H., & Najafi, E. (2018). Iran auto market price segmentation and car ranking in segments using a hybrid DEMATEL- Two-Step clustering-TOPSIS approaches and two-step weighting based on Shannon’s entropy. Industrial management studies, 16(50), 159-192. (In Persian).https://jims.atu.ac.ir/article_9110.html?lang=en