摘要
利用HTTP调试抓包工具,结合python爬虫框架对国内微信公众平台中的数据进行采集,并将其存储在Mongo DB数据库中。利用微信传播指数算法分析国内公共图书馆微信公众平台的信息传播能力,引入机器学习中的LDA模型对国内公共图书馆微信公众平台中信息的主题进行分类,总结不同主题中高传播能力信息的特征。
The data collected from the WeChat public platforms in domestic provincial public libraries using the HTTP debugging and packet capture tool in combination with the Python crawler framework were stored in the Mongo DB Database.The information dissemination ability of the WeChat public platforms in domestic provincial public libraries was analyzed using the WeChat dissemination index algorithm.The topics of information collected from the WeChat public platforms in domestic provincial public libraries were classified by introducing them into the LDA model in machine learning and the characteristics of information with a high dissemination ability in different topics were summarized.
作者
陈莉
赵婉婧
董越
王鸑飞
董兰军
CHEN Li;ZHAO Wan-jing;DONG Yue;WANG Yue-fei;DONG Lan-jun(Institute of Agricultural Information,Chinese Academy of Agricultural Sciences,Beijing 100081,China;Document and Information Center,Chinese Academy of Sciences,Beijing 100190,China;Department of Library and Information Science and Archive Management,University of Chinese Academy of Sciences,Beijing 100190,China)
出处
《中华医学图书情报杂志》
CAS
2021年第6期35-39,共5页
Chinese Journal of Medical Library and Information Science
关键词
公共图书馆
微信公众平台
信息传播
文档主题生成模型
Public library
WeChat public platform
Information dissemination
File topic generation model