基于AToT模型的中国科技部官方微信主题量化分析

Quantitative analysis of topics editing in Ministry of Science and Technology’s WeChat official account based on AToT model

中国科学技术部已将微信等社交媒体应用于科技管理,“锐科技”是科技部官方微信公众号。与传统科技类报刊、期刊的编辑手段不同,“锐科技”微信公众号在选稿和推送上有自身特点。采用后验概率主题模型对“锐科技”和其子公众号“锐动源”的稿件内容进行量化分析和挖掘,揭示了科技部官方微信选稿内容随时间变化的规律;通过研究科技工作者阅读偏好,展示了文章主题与读者浏览量之间的关系,有助于提高科技类新媒体的编辑和水平,增强科技宣传效果,更好地理解中国科技管理的思路。

Like the Facebook,the Twitter and the TikTok,the WeChat is a well-known mobile instant messaging product with over 1 billion active accounts,and it supports text messages,voices,videos,pictures and payments.The Ministry of Science and Technology of the People's Republic of China makes the science and technology management through various social media,including the WeChat,and the"Rui Ke Ji(Sharp S&T)"is the official WeChat account of the Ministry of Science and Technology,providing information for scientists and technicians.Unlike the editing of the traditional science and technology newspapers and periodicals,the WeChat official account"Rui Ke Ji"has its own characteristics in the manuscript selection and publication(push).In order to see the coverage of the topics of the WeChat articles changing over the time and the relationship between the topics of the articles and the view accounts,a Bias probability topic model,AToT,is used to quantitatively analyze and mine the contents of the articles in the"Rui Ke Ji"and its sub account the"Rui dong yuan(Sharp Dynamic Source)"in this paper.The results reveal where the ministry’s publicity lies and how the topics of the articles change over the time.The reading preferences of Chinese scientists and technicians are analyzed and it is shown that there is a certain relationship between the contents of the WeChat articles and the page views.This study helps to improve the editing level of the new media and the science and technology publicity.