Browse > Article
http://dx.doi.org/10.22937/IJCSNS.2021.21.2.17

Courses Recommendation Algorithm Based On Performance Prediction In E-Learning  

Koffi, Dagou Dangui Augustin Sylvain Legrand (Unite de Formation et de Recherche des Mathematiques et Informatique (UFR-MI), Universite Felix Houphouet-Boigny (UFHB))
Ouattara, Nouho (Laboratoire de Recherche en Informatique et Telecommunication (LARIT) Universite Felix Alassane Ouattara (UAO))
Mambe, Digrais Moise (Laboratoire de Recherche en Informatique et Telecommunication (LARIT) Universite Nangui Abrogoua (UNA))
Oumtanaga, Souleymane (Laboratoire de Recherche en Informatique et Telecommunication (LARIT) Institut National Polytechnique Felix Houphouet-Boigny (INPHB))
ADJE, Assohoun (Unite de Formation et de Recherche des Mathematiques et Informatique (UFR-MI), Universite Felix Houphouet-Boigny (UFHB))
Publication Information
International Journal of Computer Science & Network Security / v.21, no.2, 2021 , pp. 148-157 More about this Journal
Abstract
The effectiveness of recommendation systems depends on the performance of the algorithms with which these systems are designed. The quality of the algorithms themselves depends on the quality of the strategies with which they were designed. These strategies differ from author to author. Thus, designing a good recommendation system means implementing the good strategies. It's in this context that several research works have been proposed on various strategies applied to algorithms to meet the needs of recommendations. Researchers are trying indefinitely to address this objective of seeking the qualities of recommendation algorithms. In this paper, we propose a new algorithm for recommending learning items. Learner performance predictions and collaborative recommendation methods are used as strategies for this algorithm. The proposed performance prediction model is based on convolutional neural networks (CNN). The results of the performance predictions are used by the proposed recommendation algorithm. The results of the predictions obtained show the efficiency of Deep Learning compared to the k-nearest neighbor (k-NN) algorithm. The proposed recommendation algorithm improves the recommendations of the learners' learning items. This algorithm also has the particularity of dissuading learning items in the learner's profile that are deemed inadequate for his or her training.
Keywords
Algorithm; deep learning; recommendation system; collaborative approach; e-learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J. Delporte, « Factorisation matricielle, application a la recommandation personnalisee de preferences », thesis, Rouen, INSA, 2014.
2 S. M. Nafea, F. Siewe, et Y. He, « A Novel Algorithm for Course Learning Object Recommendation Based on Student Learning Styles », in 2019 International Conference on Innovative Trends in Computer Engineering (ITCE), fevr. 2019, p. 192-201, doi: 10.1109/ITCE.2019.8646355.   DOI
3 J. Lu, D. Wu, M. Mao, W. Wang, et G. Zhang, « Recommender system application developments: A survey », Decision Support Systems, vol. 74, p. 12-32, juin 2015, doi: 10.1016/j.dss.2015.03.008.   DOI
4 J. K. Tarus, Z. Niu, et D. Kalui, « A hybrid recommender system for e-learning based on context awareness and sequential pattern mining », Soft Comput, vol. 22, no 8, p. 2449-2461, avr. 2018, doi: 10.1007/s00500-017-2720-6.   DOI
5 B. Alhijawi, G. Al-Naymat, N. Obeid, et A. Awajan, « Novel predictive model to improve the accuracy of collaborative filtering recommender systems », Information Systems, vol. 96, p. 101670, fevr. 2021, doi: 10.1016/j.is.2020.101670.   DOI
6 A. Al-Badarenah et J. Alsakran, « An Automated Recommender System for Course Selection », ijacsa, vol. 7, no 3, 2016, doi: 10.14569/IJACSA.2016.070323.   DOI
7 C. K. Pereira, F. Campos, V. Stroele, J. M. N. David, et R. Braga, « BROAD-RSI - educational recommender system using social networks interactions and linked data », J Internet Serv Appl, vol. 9, no 1, p. 7, mars 2018, doi: 10.1186/s13174-018-0076-5.   DOI
8 H. Jiang, « Non-Asymptotic Uniform Rates of Consistency for k-NN Regression », AAAI, vol. 33, no 01, Art. no 01, juill. 2019, doi: 10.1609/aaai.v33i01.33013999.   DOI
9 O. Bourkoukou et E. E. Bachari, « Toward a Hybrid Recommender System for E-learning Personnalization Based on Data Mining Techniques », JOIV : International Journal on Informatics Visualization, vol. 2, no 4, Art. no 4, aout 2018, doi: 10.30630/joiv.2.4.158.   DOI
10 S. Asadi, S. M. B. Jafari, et Z. Shokrollahi, « Developing a Course Recommender by Combining Clustering and Fuzzy Association Rules », Journal of AI and Data Mining, vol. 7, no 2, p. 249-262, avr. 2019, doi: 10.22044/jadm.2018.6260.1739.   DOI
11 X. Liu, « A collaborative filtering recommendation algorithm based on the influence sets of e-learning group's behavior », Cluster Comput, vol. 22, no 2, p. 2823-2833, mars 2019, doi: 10.1007/s10586-017-1560-6.   DOI
12 D. D. A. S. L. Koffi, T. N'takpe, A. Adje, et S. Oumtanaga, « A New Approach to Predicting Learner Performance with Reduced Forgetting », International Journal of Advanced Computer Science and Applications (IJACSA), vol. 11, no 5, Art. no 5, 41/30 2020, doi: 10.14569/IJACSA.2020.0110532.   DOI
13 Z. Gulzar, A. A. Leema, et G. Deepak, « PCRS: Personalized Course Recommender System Based on Hybrid Approach », Procedia Computer Science, vol. 125, p. 518-524, janv. 2018, doi: 10.1016/j.procs.2017.12.067.   DOI
14 S. M. Nafea, F. Siewe, et Y. He, « On Recommendation of Learning Objects Using Felder-Silverman Learning Style Model », IEEE Access, vol. 7, p. 163034-163048, 2019, doi: 10.1109/ACCESS.2019.2935417.   DOI
15 Y. LeCun, Y. Bengio, et G. Hinton, « Deep learning », Nature, vol. 521, no 7553, Art. no 7553, mai 2015, doi: 10.1038/nature14539.   DOI
16 L. Deng et D. Yu, « Deep Learning: Methods and Applications », Found. Trends Signal Process., vol. 7, no 3-4, p. 197-387, juin 2014, doi: 10.1561/2000000039.   DOI
17 F. Wang, Z. Liu, et C. Wang, « An improved kNN text classification method », International Journal of Computational Science and Engineering, vol. 20, no 3, p. 397-403, janv. 2019, doi: 10.1504/IJCSE.2019.103944.   DOI
18 H. N. T. Diem, « Personalized Course Recommendation in Formal Learning Based on Logistic Regression », 2015, doi: 10.17148/IJARCCE.2015.410119.   DOI
19 J. Xiao, M. Wang, B. Jiang, et J. Li, « A personalized recommendation system with combinational algorithm for online learning », J Ambient Intell Human Comput, vol. 9, no 3, p. 667-677, juin 2018, doi: 10.1007/s12652-017-0466-8.   DOI
20 A. Swetapadma et A. Yadav, « A novel single-ended fault location scheme for parallel transmission lines using k-nearest neighbor algorithm », Computers & Electrical Engineering, vol. 69, p. 41-53, juill. 2018, doi: 10.1016/j.compeleceng.2018.05.024.   DOI
21 N. Maleki, Y. Zeinali, et S. T. A. Niaki, « A k-NN method for lung cancer prognosis with the use of a genetic algorithm for feature selection », Expert Systems with Applications, vol. 164, p. 113981, fevr. 2021, doi: 10.1016/j.eswa.2020.113981.   DOI
22 S. B. Aher et L. M. R. J. Lobo, « Combination of machine learning algorithms for recommendation of courses in E-Learning System based on historical data », Knowledge-Based Systems, vol. 51, p. 1-14, oct. 2013, doi: 10.1016/j.knosys.2013.04.015.   DOI
23 D. Kurniadi, E. Abdurachman, H. L. H. S. Warnars, et W. Suparta, « The prediction of scholarship recipients in higher education using k-Nearest neighbor algorithm », IOP Conf. Ser.: Mater. Sci. Eng., vol. 434, p. 012039, dec. 2018, doi: 10.1088/1757-899X/434/1/012039.   DOI
24 H. Zhang, T. Huang, Z. Lv, S. Liu, et H. Yang, « MOOCRC: A Highly Accurate Resource Recommendation Model for Use in MOOC Environments », Mobile Netw Appl, vol. 24, no 1, p. 34-46, fevr. 2019, doi: 10.1007/s11036-018-1131-y.   DOI
25 S. Wan et Z. Niu, « A Hybrid E-Learning Recommendation Approach Based on Learners' Influence Propagation », IEEE Transactions on Knowledge and Data Engineering, vol. 32, no 5, p. 827-840, mai 2020, doi: 10.1109/TKDE.2019.2895033.   DOI
26 N. Rusk, « Deep learning », Nature Methods, vol. 13, no 1, Art. no 1, janv. 2016, doi: 10.1038/nmeth.3707.   DOI
27 O. Bourkoukou et O. Achbarou, « Weighting based approach for learning resources recommendations », JOIV : International Journal on Informatics Visualization, vol. 2, no 3, Art. no 3, avr. 2018, doi: 10.30630/joiv.2.3.124.   DOI
28 J. Shu, X. Shen, H. Liu, B. Yi, et Z. Zhang, « A content-based recommendation algorithm for learning resources », Multimedia Systems, vol. 24, no 2, p. 163-173, mars 2018, doi: 10.1007/s00530-017-0539-8.   DOI
29 S. B. Aher, « EM&AA: An Algorithm for Predicting the Course Selection by Student in e-Learning Using Data Mining Techniques », J. Inst. Eng. India Ser. B, vol. 95, no 1, p. 43-54, janv. 2014, doi: 10.1007/s40031-014-0074-3.   DOI
30 H. Imran, M. Belghis-Zadeh, T.-W. Chang, Kinshuk, et S. Graf, « PLORS: a personalized learning object recommender system », Vietnam J Comput Sci, vol. 3, no 1, p. 3-13, fevr. 2016, doi: 10.1007/s40595-015-0049-6.   DOI