摘要
为了快速获取用户感性评价并用于产品的改进设计,提出一种基于在线评论挖掘的产品感性评价方法。采用爬虫技术从网络平台获取用户对产品的在线评论数据,构建在线评论原始语料库;通过分词技术和词向量技术预处理数据,将文本评论转化为词向量表达形式;挖掘在线评论数据,构建用户极性词典并获取产品特征;分析用户关注特征和在线评论数据,为制造企业提出产品改进措施。最后以笔记本电脑为例,基于在线评论和产品规格说明书,构建在线评论原始语料库并进行数据预处理,获取产品特征,分析用户评价,验证所提理论与方法的可行性和有效性,为改进产品设计提供依据。
In order to quickly obtain the users′perceptual evaluation for improving the product design,a method of product perceptual evaluation based on online review mining was proposed.The web crawler technology was used to gain the users′online review data about product from the network platforms and the raw corpus was built.Using the participle technology and word embedding technology,the text review data was preprocessed and transformed into the expression form of word embedding.The online review data was mined to obtain the user polarity dictionary and the product characteristics.The characteristics concerned by users and their evaluations were analyzed and the suggestions on product improvement were given for the manufacturing enterprise.Finally,taking the notebook computer as an example,the raw corpus was constructed and preprocessed based on the online review and product specification,the product characteristics were obtained,the user evaluations were analyzed,the feasibility and effectiveness of the proposed theory and method were verified,and the references for improving product design were provided.
作者
高新勤
金雨昊
王雪萍
郝娟
GAO Xinqin;JIN Yuhao;WANG Xueping;HAO Juan(School of Mechanical and Precision Instrumental Engineering,Xi’an University of Technology,Xi’an 710048,China;School of Economics and Finance,Xi’an Jiaotong University,Xi’an 710061,China)
出处
《现代制造工程》
CSCD
北大核心
2021年第12期13-20,共8页
Modern Manufacturing Engineering
基金
国家自然科学基金资助项目(51575443)
陕西省教育厅重点科学研究计划项目(20JY047)
工信部工业互联网平台测试床建设项目(TC19083W8)。
关键词
在线评论
感性工学
文本挖掘
产品特征
极性词典
改进设计
online review
Kansei engineering
text mining
product characteristic
polarity dictionary
design improvement
