Fast recommendation of literature materials in smart libraries based on improved collaborative filtering algorithm
Bin Liu · International Journal of Computer Applications in Technology · 2024
To overcome the issues of low accuracy and recall rate, as well as long response time in traditional recommendation methods, a fast recommendation method of literature materials in smart libraries based on improved collaborative filtering algorithm is proposed. The FCM clustering algorithm is used to cluster the knowledge in literature materials in the smart library that enables knowledge discovery. The feature words by the knowledge texts are determined using the VSM model and TF-IDF algorithm, and a LDA topic model is employed to identify the topics in the knowledge texts. The collaborative filtering algorithm is improved through matrix factorisation, and the improved algorithm is utilised for fast recommendation of literature materials in the smart library. The experimental results show that the proposed method achieves a highest recall rate of 99.1%, a highest accuracy rate of 98.8%, with a response time below 72 ms, indicating good recommendation performance.