Implementation of Efficient Online English Learning System and Student Performance Prediction Using Linear K-Nearest Neighbors (L-Knn) Method

Technical assistance for the establishment of a distance learning environment for learning English is provided by the advancement of information technology and the educational information process. People are still getting used to online teaching methods, and it is becoming more widely accepted. E-learning and online education have advanced significantly in recent years. The teaching paradigm has moved from traditional classroom learning to dynamic web-based learning. As a result, instead of static information, learners have received dynamic learning material tailored to their abilities, requirements, and preferences. To improve the English learning material efficiency, this paper implements an online English learning system based on efficient learning material selection. The English learning materials are preprocessed using normalization. The dimensionality reduction of the data is done using the Kernel-based-Independent Component Analysis (K-ICA). Data classification is performed using the Hypothetical Naïve Bayes Algorithm (HNBA). The student performance like learning efficiency, interactive accuracy rate, and artistic skills are predicted using the linear k-Nearest Neighbors (L-KNN). The proposed system can be simulated by employing the MATLAB tool and the performance is compared with other conventional methodologies. The findings of this study reveal that the presented online learning method may significantly increase students' oral and written skills.