Electronic Information Professional English Learning System Using Recurrent Neural Network-Collaborative Filtering Recommendation Algorithm

E-learning is one of the significant technologies in online education in long-lasting terms with contrast to customary process of head-to-head educating culture for electronic information. By e-learning, a numerous learners have benefited from various programs. This research considers Electronic Information Professional English learning system as the foundation and establishes the recommendation system for learning of English vocabulary using Recurrent Neural Network-Collaborative Filtering (RNN-CF). Initially, data is gathered from 100 individuals for an electronic information professional English vocabulary e-learning system like text. The stemming and stop word removal is employed to remove unwanted words. Term-Frequency-Inverse Document Frequency (TF-IDF) and Word2vec are used for feature extraction to calculate essential words. RNN-CF is performed for Professional English learning recommendation system which includes a Gated Recurrent Unit (GRU) layer in Neural Collaborative Filtering (NCF). The proposed RNN-CF achieves a better accuracy of 96.25% compared to existing techniques like Convolutional Neural Network-CF (CNN-CF), Long Short-Term Memory-CF (LSTM-CF), and GRU-CF respectively.