基于朴素贝叶斯的学术论文推荐算法研究  

Academic paper recommendation algorithm based on Naive Bayes

作　　者：严海兵[1] 周刚 朱振刚 杨萌[1] YAN Haibing;ZHOU Gang;ZHU Zhengang;YANG Meng(Library,SUST,Suzhou 215009,China;Schoool of Mechanical Engineering,SUST,Suzhou 215009,China)

机构地区：[1]苏州科技大学图书馆,江苏苏州215009 [2]苏州科技大学机械工程学院,江苏苏州215009

出　　处：《苏州科技大学学报（自然科学版）》2023年第4期69-75,共7页Journal of Suzhou University of Science and Technology（Natural Science Edition）

基　　金：国家社会科学基金项目(18BTQ060);江苏高校哲学社会科学研究项目(2023SJYB1436)。

摘　　要：文献资源推荐算法是数字图书馆智慧化的关键技术,学术论文是数字图书馆中交流最为活跃的主体,利用推荐算法提升学术论文的有效利用率具有重要意义。当前主流文献资源推荐算法是通过对文献或者用户建立特征向量模型,再计算向量间的相似度,根据相似度为用户进行资源推荐。论文中的研究是利用学术论文的特征词为目标用户建立学术画像,再利用朴素贝叶斯模型计算论文符合用户学术画像的后验概率,根据论文的后验概率大小,向目标用户推荐论文资源。通过模拟测试该推荐算法在查准率P、召回率R、F1分数、程序运行时间各方面均优于传统推荐算法。这种预估用户访问学术论文概率的方法,也为图书馆个性化推荐服务提供了新的思路。The literature resource recommendation algorithm is a key technology for the intelligence of digital libraries,and academic papers are the most active subjects of communication in digital libraries.It is of great significance to use recommendation algorithms to improve the effective utilization rate of academic papers.The current mainstream literature resource recommendation algorithm is to establish a feature vector model for literature or users,calculate the similarity between vectors,and recommend resources to users based on the similarity.This study is to use the characteristic words of academic papers to establish academic portraits for target users,and then use the Naive Bayesian model to calculate the posterior probability that the paper conforms to the user’s academic portraits.According to the posterior probability of the paper,the paper resources are recommended to target users.Through simulation testing,this recommendation algorithm outperforms traditional recommendation algorithms in terms of precision P,recall R,F1 score,and program runtime.This method of estimating the probability of users accessing academic papers can also provide new ideas for personalized recommendation services in libraries.

关 键 词：文本推荐算法 朴素贝叶斯 数字图书馆 个性化推荐 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]