Construction of Personalized Learning Content Recommendation System Based on Recommendation Algorithm in English Learning

Abstract

English is currently a valuable information transmission medium for quickly acquiring many cutting-edge technology and professional skills. Traditional English learning has very limited time and space, therefore teachers unable to present students with enough English learning information. This manuscript proposes a construction of personalized learning content Recommendation system based on recommendation algorithm in English learning (CPLRS-EL-RA).Initially, the data is collected from Movielens-1M dataset. Then, the collected data are fed to pre-processing. In pre-processing, Generalized Moment Kalman Filter (GMKF) is utilized to clean the data. Then the pre-processing output is supplied to the feature extraction using Enhanced Synchro extracting Wavelet Transform (ESWT) for extracting the students’ attitude, relationship and entities. Afterward, the extracted output is fed to the recommendation algorithm. The recommendation algorithm effectively classifies each student's learning into listening, speaking, reading and writing. The Tiger Beetle Optimizer (TBO) is used to optimize the weight parameter of Recommendation Algorithm. The proposed method is activated in Python and the efficiency is estimated under metrics, like accuracy, precision, recall, sensitivity, specificity and computation time. The CPLRS-EL-RA method attains higher accuracy 22.32%, 31.25% and29.31%, higher sensitivity 27.32%,24.43%, 38.24% and higher recall 31.13%, 23.33% and 38.13%for listening analysed to the existing methods, like Personalized Recommendation System for English Teaching Resources (PRSETR-CRNN),Learner comments-based Recommendation system(LCBRS-CNN), and Hybrid recommendation system combined content(HRSC-ANN)respectively.