الكلمات المفتاحية
Weka Workbench
College Admission
Decision Trees
Naïve Bayes
Nearest Neighbor
Class Attribute
Prediction
Classification
Attribute Selection
How to Cite
الملخص
It is clear to everyone that the College admission process is a strategic process at the country level, and is very important for citizens of all categories. This process receives attention from all divisions of society, students, their families and the educational sector in general, so it was necessary to pay attention to the smallest details, and try to improve and simplify it. The Directorate of Information and Communications Technology in the Ministry of Higher Education and Scientific Research in Syria adopts the announcements issued by the ministry to implement trade-offs electronically, and these announcements are considered as the regulator for the work of software programs. This study aimed to employ college admission data for the scientific branch gathered during the previous ten years, and use it to create a predictive model that applies to new students coming to college admission. The most important results of the study were:
Designing a predictive model using the WEKA workbench for data mining, using the college admission data gathered during the previous ten years, and apply it to students of the scientific branch coming to college admission. This model is used to guide students to the university and the appropriate college for them, according to their data, and using the model for decision support in the Ministry of Higher Education and Scientific Research to contribute to assign the appropriate seats for colleges and institutes in all Syrian Governmental universities, before starting college admission process.
References
2. Alex A. Freitas. (2002). Data Mining and Knowledge Discovery with Evolutionary Algorithms. Berlin, Germany: Springer.
3. Mwapashua H. Fujo and Mussa Ally Dida. (2018). Web-based admission system for advanced level, private schools: case of Kilimanjaro region, Tanzania . International Journal of Advanced Technology and Engineering Exploration, 5(47)(2394-7454), 407-418.
4. Annam Mallikharjuna Roa, Nagineni Dharani, A. Satya Raghava, J. Buvanambigai and K. Sathish. (2018). College Admission Predictor . Journal of Network Communications and Emerging Technologies (JNCET), 8(4), 142-147.
5. Ian H. Witten and Eibe Frank . (2005). Data Mining Practical Machine Learning Tools and Techniques 2nd Edition. Elsevier.
6. J. Ross Quinlan. (1994). C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, Inc.
7. Baswana, S., Chakrabarti, P. P., Patanged, U., Kanoria, Y., & Chandran, S. (2019, September - October). Centralized Admissions for Engineering Colleges in India. INFORMS JOURNAL ON APPLIED ANALYTICS, pp. 338-354.
8. Janusz Sobecki. (2006). Implementations of Web-based Recommender Systems Using Hybrid Methods . International Journal of Computer Science & Applications, 3(3), 53-64.
9. R. Suguna and D. Sharmila. (2013). An Efficient Web Recommendation System using Collaborative Filtering and Pattern Discovery Algorithms. International Journal of Computer Applications,(0975-8887). 37-70.
10. الشربيني الهلالي. (نيسان, 2008). نظام مقترح للقبول بمؤسسات التعليم العالي في مصر. اللجنة التحضيرية للمؤتمر القومي لتطوير الثانوية العامة وسياسات القبول في التعليم العالي في مصر.
11. قصي عزام. (2015). نظام دعم القرارات المتعلقة بالقبول الجامعي (المفاضلة) في الجمهورية العربية السورية. دمشق: المعهد العالي للعلوم التطبيقية والتكنولوجيا.
12. نصرة رضا البناي، وفاء محمد بلحاضي، و محمد أحمد الخولي. (2004). القيمة التنبؤية لمعايير القبول المستخدمة بجامعة قطر وعلاقتها بالمعدل التراكمي الجامعي.
13. هيفاء ابراهيم. (2013). أنموذج مقترح لتطوير واقع سياسات قبول الطلبة في التعليم الجامعي في الجمهورية العربية السورية في ضوء تجارب بعض الدول المتقدمة. جامعة دمشق - كلية التربية، سورية.