A Collaborative Recommendation Algorithm for Course Resources in Multimedia Distance Education Based on Fuzzy Association Rules

Currently, the homogenization of vast multimedia distance education course resources is becoming increasingly severe. In the process of learning habit characteristics, the association rules become more diverse, showing typical fuzzy attributes, which leads to obvious drawbacks in the recommendation behavior based solely on association rules. A multimedia distance education course resource recommendation algorithm based on fuzzy association rules is designed. Using fuzzy clustering methods, the fuzzy membership degree of multimedia distance education course resources is calculated to generate frequent fuzzy item sets, and association rules are generated from the frequent fuzzy item sets to solve the problem of feature homogenization in course resource recommendations. Adaptive mutation operators and adaptive crossover operators are used to optimize the fuzzy association rule mining process, mining the fuzzy association rules of multimedia distance education course resources. A user-based collaborative filtering recommendation method is used to calculate the similarity of user ratings for course resources in the results of fuzzy association rule mining, obtaining the target user's rating for course resources. Based on the scoring ranking results, the course resource recommendation results are output. The linguistics courses of the Japanese major are taken as the experimental subjects, and the experimental results show that this method can provide users with the required Japanese translation course resources, with a recommendation hit rate higher than 0.9.