摘要
为比较科普类微博互动性,推进科普工作建设,选用评论的回复总数评价互动性,以微博博主"科普君Xueshu"为样本,建立零膨胀负二项模型探究影响因素,使用Stata统计软件进行拟合,计算模型各参数.结果显示,配图、视频、文字数(0-50字)、插入话题等因素对回复总数有正向促进作用;时间(13-19时)和外文词汇的使用会降低互动性.
In order to compare the interactivity of science popularization weibo posts and promote the construction of scientific popularization work, this paper chooses the total number of replies to evaluate the interactivity,taking the posts of the blogger '科普君 Xueshu' as the sample, establishes the Zero-Inflated negative binomial model to explore the determinant factors, and uses the Stata statistical software to fit the model and estimate the parameters.The results show that the factors such as photo, video, Word count(0-50 words) and topic have positive effects on the total number of replies;post time(13-19) and the use of foreign words reduce the interactivity.
作者
刘基伟
闵素芹
李少鹏
LIU Ji-wei;MIN Su-qin;LI Shao-peng(School of Science,Communication University of China,Beijing 100024, China;Fox School of Business,Temple University,Philadelphia 19122, USA)
出处
《数学的实践与认识》
北大核心
2019年第9期100-106,共7页
Mathematics in Practice and Theory
基金
中央高校基本科研业务费专项资金资助(3132018XNG1830)
关键词
互动性
回复总数
零膨胀负二项回归模型
interactivity
total number of replies
zero-inflated negative binomial regression model
