基于协同过滤与概率主题模型的大学生行为模式挖掘研究  

Research on College Students'Behavior Pattern Mining Based on Collaborative Filtering and Probabilistic Topic Model

作　　者：刘涛[1] LIU Tao(School of Computer and Big Data Science,Jiujiang University,Jiujiang 332005,China)

机构地区：[1]九江学院计算机与大数据科学学院,江西九江332005

出　　处：《现代信息科技》2023年第24期45-48,共4页Modern Information Technology

基　　金：江西省教育科学“十三五”规划2020年度课题(20YB206);江西省高校人文社会科学研究2021年度课题(JY21225)。

摘　　要：大学生个体多样性的增强使得高校的教育管理面临前所未有的挑战。在教育大数据环境下,如何利用数据挖掘技术从海量校园行为数据中挖掘出有价值的信息变得尤为重要。针对校园行为数据存在稀疏性的问题,提出一种基于协同过滤与概率主题模型的大学生行为模式挖掘方法;采用Hawkes过程模拟产生事件并使用自定义指标评估模型性能,结果表明模型能有效挖掘出大学生行为模式。最后从同伴数量与类别选择的角度分析了大学生行为模式。The enhancement of individual diversity among college students poses unprecedented challenges to the education management of universities.In the education big data environment,it has become particularly important to use data mining technology to extract valuable information from massive campus behavior data.A method for mining college student behavior patterns based on collaborative filtering and probabilistic topic models is proposed to address the sparsity of campus behavior data;the Hawkes process is used to simulate the generation of events and custom metrics are used to evaluate the performance of the model.The results show that the model can effectively mine behavior patterns of college students.Finally,the behavioral patterns of college students are analyzed from the perspectives of peer quantity and category selection.

关 键 词：协同过滤 概率主题模型 校园行为 行为模式 Hawkes过程 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] G647[自动化与计算机技术—计算机科学与技术]