融合LDA主题模型和支持向量机的商品个性化推荐方法  

Commodity Personalized Recommendation Method Integrating LDA Topic Model and Support Vector Machine

作　　者：穆晓霞[1,2] 董星辉 柴旭清[1] 李钧涛[3] MU Xiaoxia;DONG Xinghui;CHAI Xuqing;LI Juntao(College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, China;Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province, Henan Normal University, Xinxiang 453007,China;College of Mathematics and Information Science, Henan Normal University, Xinxiang 453007,China)

机构地区：[1]河南师范大学计算机与信息工程学院,河南新乡453007 [2]河南师范大学教育人工智能与个性化学习,河南省重点实验室,河南新乡453007 [3]河南师范大学数学与信息科学学院,河南新乡453007

出　　处：《郑州大学学报（理学版）》2022年第3期34-39,共6页Journal of Zhengzhou University:Natural Science Edition

基　　金：国家自然科学基金项目(61203293,31700858);河南省科技攻关项目(212102210140)。

摘　　要：针对网络商品评论数据不能有效引导买方做出合理选择的问题,提出一种融合LDA主题模型和支持向量机的商品个性化推荐方法。首先爬取不同类型商品的用户评论数据并对其进行预处理;其次建立基于LDA的主题模型并对其特点进行量化;最后利用支持向量机实现商品个性化推荐。以智能手机商品为例进行实验分析,结果表明,所提方法能获得98%以上的分类精度。Aiming at the problem that online commodity review data could not effectively guide buyers to make reasonable choices,a commodity personalized recommendation method integrating LDA topic model and support vector machine was proposed.Firstly,the user comment data of different types of goods were crawled and preprocessed.Secondly,the topic model based on LDA was established and its characteristics was quantified.Finally,support vector machine was used to realize commodity personalized recommendation.The experimental results on smart phone products showed that the proposed method could achieve more than 98%classification accuracy.

关 键 词：LDA主题模型 支持向量机 粒子群优化 个性化推荐 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]