Personalized Recommendation Algorithm for Optimizing English Vocabulary Learning Using Neural Networks

Learning vocabulary is the process of gaining the foundational knowledge needed to acquire a second language. The majority of children learn vocabulary by accident when they are exposed to words indirectly at home and school by chatting and listening, reading aloud from books, and engaging in extensive independent reading. Accurate spelling, precise pronunciation, appropriate word usage, and efficient vocabulary retention or remembering are among the challenges associated with acquiring English vocabulary. In this, we proposed a novel student psychology optimized intellectual deep neural network (SPO-IDNN) for personalized recommendations of English vocabulary learning. Optimizing feature learning and temporal information processing enhances the model’s capacity to acquire language across various textual contexts. In this study, we collected the data from the wiki dataset used to classify English words. Data preprocessing techniques that preprocess the gathered text using stemming, lemmatization, punctuation, special character removal, stop word removal, and case normalization improve understanding and memory of English vocabulary acquisition. TF-IDF facilitates the learning of English vocabulary to find essential words in documents. The classification task, considering temporal dependencies, was achieved using our proposed model. The proposed method is compared to the other traditional algorithms. Implemented in Python, our approach focuses on English vocabulary learning performance metrics. The overall performance in terms of recall (0.98), accuracy (0.97), and F1-score (0.96). The result shows the proposed method has achieved better performance. English speakers will benefit from this study’s efficient and accurate natural language processing technologies, which will facilitate language application and understanding while also enhancing vocabulary development and comprehension.