A Personalized Recommendation Method for Teaching Resources of Western Literature Course Based on Collaborative Filtering Algorithm

Abstract

This paper a study of selected major works of Western Literature Course based on collaborative filtering Algorithm. Europe from the ancient world and Renaissance to the present, with attention to their historical and literary settings. This course provides insights into such issues as identity, authority, emotions, relationships and social change and structures, from a broad palette of significant writers. Students develop their ability to recognize literary themes, authorial style and the connections between literature and history. The method for suggesting redid learning resources is introduced in this exploration and depends on a unique collaborative filtering algorithm. Collaborative filtering is the method of recommendation that is most often used. An asset the board framework in light of a better collaborative recommendation algorithm is proposed to resolve the issues of "lost" and "squandered" Western Literature Courses and to additional raise the use worth of different English teaching resources. The framework's utilization cases are first analyzed to acknowledge it. A half breed recommendation algorithm is used to prescribe the learning materials to build the exactness of the recommendations by coordinating the expert characteristics and different properties of the accomplished clients. Ultimately, to some extent fabricated point of interaction is given. Exploratory outcomes show that the better algorithm successfully tackled the deficiency of direction in learning, and the similitude and precision of suggested learning resources outperformed 90%. Our algorithm can completely fulfill the personalized necessities of understudies, and give a reference answer for the personalized schooling administration of keen internet learning stages. As per exploratory discoveries, the upgraded algorithm effectively tended to the deficiency of direction in learning, and the likeness and precision of recommended learning resources surpassed 90%. Our algorithm can totally meet understudies' individualized requirements and proposition a model reaction to the personalized training administration presented by complex internet learning stages.