By: Preetham S, Chandrashekhar MC, and MZ Kurian
1-Student, Department of Electronics and Communication Engineering, Sri Siddhartha Institute of Technology, Tumakuru, Karnataka 572105, India
2-Student, Department of Electronics and Communication Engineering, Sri Siddhartha Institute of Technology, Tumakuru, Karnataka 572105, India
3-Department of Electronics and Communication Engineering, Sri Siddhartha Institute of Technology, Tumakuru, Karnataka 572105, India
With the explosion of electronic devices and internet technologies in today’s world, the amount of data we store has grown massively. Data is simply information that has been organized in a way that makes it easy to share or work with. A potent technology that enables computers to learn from data without direct programming is machine learning, which we employ in our research. The focus of this study is on the development of prediction models using machine learning, particularly for e-learning platforms. By analyzing data such as student engagement, quiz scores, and interaction patterns, the model can predict how well students will perform and even identify those who might need extra help or are at risk of falling behind. We investigated several machines learning methods, including neural networks, support vector machines (SVM), and decision trees, to see which is most effective for these predictions. Machine learning helps make e-learning more personalized by figuring out how well students might do and suggesting courses that suit their abilities and interests. It looks at things like study habits and quiz results to spot students who may need extra help. While this makes learning more flexible, there are some challenges, like needing good data, protecting privacy, and making sure the system treats all students fairly. If done carefully, machine learning can make e-learning much better for everyone.
Keywords: E-learning, Machine Learning, Naïve Bayes, Evaluation, SVM
Citation:
Refrences:
[1]. Xia M, Wei H, Xu M, Lo LY, Wang Y, Zhang R, Qu H. Visual analytics of student learning behaviors on k-12 mathematics e-learning platforms. arXiv preprint arXiv:1909.04749. 2019 Sep 7.
[2]. Wang X, Wu P, Liu G, Huang Q, Hu X, Xu H. Learning performance prediction via convolutional GRU and explainable neural networks in e-learning environments. Computing. 2019 Jun 1; 101:587-604.
[3]. De Morais AM, Araujo JM, Costa EB. Monitoring student performance using data clustering and predictive modelling. In2014 IEEE frontiers in education conference (FIE) proceedings 2014 Oct 22 (pp. 1-8). IEEE.
[4]. Injadat M, Moubayed A, Nassif AB, Shami A. Multi-split optimized bagging ensemble model selection for multi-class educational data mining. Applied Intelligence. 2020 Dec;50(12):4506-28.
[5]. Moubayed A, Injadat M, Shami A, Lutfiyya H. Relationship between student engagement and performance in e-learning environment using association rules. In2018 IEEE world engineering education conference (EDUNINE) 2018 Mar 11 (pp. 1-6). IEEE.
[6]. Kori K, Pedaste M, Altin H, Tõnisson E, Palts T. Factors that influence students’ motivation to start and to continue studying information technology in Estonia. IEEE Transactions on Education. 2016 Feb 29;59(4):255-62.
[7]. Fok WW, He YS, Yeung HA, Law KY, Cheung KH, Ai YY, Ho P. Prediction model for students’ future development by deep learning and tensorflow artificial intelligence engine. In2018 4th International Conference on information management (ICIM) 2018 May 25 (pp. 103-106). IEEE.
[8]. Shahiri AM, Husain W. A review on predicting student’s performance using data mining techniques. Procedia Computer Science. 2015 Jan 1; 72:414-22.
[9]. Quadri MM, Kalyankar NV. Drop out feature of student data for academic performance using decision tree techniques. Global Journal of Computer Science and Technology. 2010 Apr;10(2):2-5.
