Intelligent Recommendation System for Literature Education in Primary and Secondary Schools Using Deep Learning Networks

Abstract

Literature education plays a pivotal role in fostering critical thinking, creativity, empathy, and cultural understanding among students. The traditional approaches to teach literature often face challenges in engaging students and catering to individual learning needs. There are some obstacles facing literature education, including inaccurate education, lack of varied ideas, inadequate investment, and restricted access to materials. The problems impede students' development of analytical skills and involvement in poetry education. The research proposed a novel advanced Sand cat swarm driven consecutive convolutional neural network (ASCS-CCNN) technique to investigate literature education of primary and secondary students, which improves the poetry fluency and literature strategies. Recommendation system is used to predict the best sequence of educational resource using collaborative filter. In the study, poetry data is gathered, we utilize the tokenization for data preprocessing and to extract the tokenized data, we utilize term frequency inverse document frequency (TF-IDF). The findings of the study use parameters like similarity, tone accuracy and rhyme accuracy, to evaluate student performance in poetry education. The study concludes that education in primary and secondary education improves student learning through thoughtfully selected readings that complement curricular objectives and encourage greater student involvement in appreciation of poetry.