Call for Paper - January 2022 Edition
IJCA solicits original research papers for the January 2022 Edition. Last date of manuscript submission is December 20, 2021. Read More

A Recommender System to Distinguish between Students' Levels and Evaluate their Attitudes

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Shaymaa E. Sorour, Hanan E. Abdelkader
10.5120/ijca2017915644

Shaymaa E Sorour and Hanan E Abdelkader. A Recommender System to Distinguish between Students' Levels and Evaluate their Attitudes. International Journal of Computer Applications 176(7):44-50, October 2017. BibTeX

@article{10.5120/ijca2017915644,
	author = {Shaymaa E. Sorour and Hanan E. Abdelkader},
	title = {A Recommender System to Distinguish between Students' Levels and Evaluate their Attitudes},
	journal = {International Journal of Computer Applications},
	issue_date = {October 2017},
	volume = {176},
	number = {7},
	month = {Oct},
	year = {2017},
	issn = {0975-8887},
	pages = {44-50},
	numpages = {7},
	url = {http://www.ijcaonline.org/archives/volume176/number7/28571-2017915644},
	doi = {10.5120/ijca2017915644},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Education is reinforced by identifying new students' attitudes to understand the learning process. Learning analysis is one of the most useful tools to achieve this purpose. Therefore, the present study aims to provide a Recommender System (RS) to distinguish between different students' attitudes (cognitive, emotional, and practical) by creating a dictionary to automatically group common features. In this study, freestyle comments data were collected after each lecture then were analyzed to extract words and sentences' parts (noun, verb, adjective and adverb) for extracting the most common and frequently words and phrases. Thus, a predictive and understandable model was created for the students' estimates. In this paper two types of machine learning techniques were used which are: Support Vector Machine (SVM) and Random Forest (SVM-RF). These techniques are used to extract general rules that distinguish each class of students and providing appropriate automatic feedback that helps student level performance enhancement. Precision, Recall, F-Measure and Accuracy were calculated after each lecture to verify the validity of the results. The experimental results indicated the validity of the automatic feature dictionary; SVM-RF exceeded other techniques to extract general rules.

References

  1. Amjad, A. S. (2016). Educational Data Mining & Students’ Performance Prediction, (IJACSA) International Journal of Advanced Computer Science and Applications, 7(5).. .
  2. Ayub, M., Cian A., Caliusco, M., and Reynares, E. (2014). Developing an ontology-based team recommender system using EDON method: an experience report, SADIO: Electron. J. of Inform. Operat. Res. 13 1–13.
  3. Barakat, N., Bradley, (2010): A.P.: Rule extraction from support vector machines: a review. Neurocomputing 74(1), 178{190.
  4. . Barakat, N., Diederich, J. (2004) : Learning-based rule-extraction from support vector machines. In: The 14th International Conference on Computer Theory and applications ICCTA'2004
  5. Bobadilla, J. Ortega, F., Hernando, A., and Gutièrrez, A. (2013). Recommender systems survey, Knowl.-Based Syst. 46, 109–132.
  6. Breiman, L. (2001): Decision-tree forests. Machine Learning 45(1), 5-32
  7. Carlos J., Villagr, a., Francisco J., Gallego, F., and Llorens L. (2017) Improving the expressiveness of black-box models for predicting student performance, Computers in Human Behavior, 72, 621-631.
  8. Dietmar, J., and Gerhard, F. (2013).Tutorial: Recommender Systems, International Joint Conference on Artificial Intelligence Beijing, August 4.
  9. Evandro, B., C., B.F., and Marcelo, A. S.(2017). Evaluating the effectiveness of educational data mining techniques for early prediction of students' academic failure in introductory programming courses. Computers in Human Behavior 73 247-56.
  10. Fábio, O., and Garrido, C. (2014).Masters’ Courses Recommendation: Exploring Collaborative Filtering and Singular Value Decomposition with Student Profiling, Thesis to obtain the Master of Science Degree in Information Systems and Computer Engineering.
  11. Gerard J., Baars,A., TheoStijnen, Ted, A., and Splinter,W. (2017), A Model to Predict Student Failure in the First Year of the Undergraduate Medical Curriculum, Health Professions Education 3(1), , Pp 5-14.
  12. Kaklauskas,A.(2015). Biometric and Intelligent Decision Making Support, Intelligent Systems Reference Library, Springer International Publishing Switzerland , 81, pp.195-197.
  13. Kotsiantis, S. B. (2012). Use of machine learning techniques for educational proposes: A decision support system for forecasting students' grades .Artificial Intelligence Review, 37, 331e344. Artif Intell Rev (2012) 37:331–344. DOI 10.1007/s10462-011-9234x. http://dx.doi.org/10.1007/s10462-011-9234-x.
  14. Maria, G., Shade K., and Nicolae, G. ( 2015 ) A recommender for improving the student academic performance, The 6th International Conference Edu World 2014 “Education Facing Contemporary World Issues”, 7th - 9th November 2014, Procedia - Social and Behavioral Sciences, 180, 1481 – 1488.
  15. Nguyen, T., Lucas, D., Artus, K., Lars, S.(2010). Recommender System for Predicting Student Performance, 1st Workshop on Recommender Systems for Technology Enhanced Learning, Procedia Computer Science 1, 2811–2819.
  16. Raheela, A., Agathe, M., Syed, A., Najmi,. G.(2017) Analyzing undergraduate students' performance using educational data mining, Computers & Education 113, 177-194.
  17. Rahimpour, C.B., Hamid, H., Hoda, M. (2017). User trends modeling for a content-based recommender system, Expert Systems With Applications 87,209–219.
  18. Rodriguez, A., Gago, J., Rifo, L., and Rodriguez, R. (2015). A recommender system for non-traditional educational resources: a semantic approach, J. Univ. Comput. Sci. 21 306–325.
  19. Schalk, P. D., Wick, D. P., Turner, P. R., and Ramsdell, M. W. (2011). Predictive assessment of student performance for early strategic guidance. In Frontiers in education, conference (FIE), 2011. http://dx.doi.org/10.1109/FIE.2011.6143086, S2H-S2H-5.
  20. Sebastien, F., and Fabian, L. (2017). Weighting strategies for a recommender system using item clustering based on genres, Expert Systems With Applications, 77, 105–113.
  21. Sindhuja, M, Rajalakshmi,S., Nandagopal,S.M.(2013). Prediction and Analysis of students Behavior using BARC Algorithm, International Journal on Computer Science and Engineering (IJCSE) ISSN : 0975-3397, 5(6), pp. 474-480.
  22. Yadav S. K., Bhardwaj B. K. and Pal S. (2012). Mining Education Data to Predict Student's Retention: A comparative study, International Journal of Computer Science and Information Security (IJCSIS), 10 (2), 113-117.
  23. Yasmeen, A., Wejdan, A., Al-Turaiki,J., and Muna, A.(2016). Predicting Critical Courses Affecting Students Performance: A Case Study, Symposium on Data Mining Applications, SDMA, 30 March, Riyadh, Saudi Arabi.

Keywords

Freestyle Comment Data, Rule Extraction, Recommender System, Machine Techniques