TY  - EJOU
AU  - Alotaibi, Raed 
AU  - Reyad, Omar 
AU  - Karar, Mohamed Esmail 

TI  - Efficient Intelligent E-Learning Behavior-Based Analytics of Student’s Performance Using Deep Forest Model
T2  - Computer Systems Science and Engineering

PY  - 2024
VL  - 48
IS  - 5
SN  - 

AB  - E-learning behavior data indicates several students’ activities on the e-learning platform such as the number of accesses to a set of resources and number of participants in lectures. This article proposes a new analytics system to support academic evaluation for students via e-learning activities to overcome the challenges faced by traditional learning environments. The proposed e-learning analytics system includes a new deep forest model. It consists of multistage cascade random forests with minimal hyperparameters compared to traditional deep neural networks. The developed forest model can analyze each student’s activities during the use of an e-learning platform to give accurate expectations of the student’s performance before ending the semester and/or the final exam. Experiments have been conducted on the Open University Learning Analytics Dataset (OULAD) of 32,593 students. Our proposed deep model showed a competitive accuracy score of 98.0% compared to artificial intelligence-based models, such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) in previous studies. That allows academic advisors to support expected failed students significantly and improve their academic level at the right time. Consequently, the proposed analytics system can enhance the quality of educational services for students in an innovative e-learning framework.
KW  - E-learning; behavior data; student evaluation; artificial intelligence; machine learning

DO  - 10.32604/csse.2024.053358