摘要
该文基于Scrapy框架对京东网站上笔记本电脑的评论数据进行了爬取,共爬取了32种品牌,选取其中的“联想(Leno vo)拯救者Y7000P”笔记本电脑评论数据进行分析,通过pandas提供的模糊匹配方法提取数据,并对数据进行去重、分词和停用词过滤等处理,使用wordcloud库绘制词云图,呈现出的情感数据为商家和用户提供进一步的决策。
Based on the scrapy framework,this paper crawls the comment data of notebook computers on the Jingdong website.It crawls 32 brands in total,selects the comment data of"Lenovo Savior y7000p"notebook computers for analysis,extracts the data through the fuzzy matching method provided by pandas,processes the data such as de duplication,segmentation and stop words filtering,and uses wordcloud The library draws a cloud of words,presenting emotional data for businesses and users to make further decisions.
作者
方芳
FANG Fang(Hunan Vocational College of science and technology,Changsha 410000,China)
出处
《电脑知识与技术》
2020年第6期7-9,共3页
Computer Knowledge and Technology
基金
2018年湖南科技职业学院校级课题《基于情感词典和机器学习的电商平台产品评论情感倾向性分析》(项目编号:KJ18211)。
