社交网络上议题社群的公共焦虑研究， 中国人民大学新闻学院塔娜讲师，第八届全国社会媒体处理大会SMP2019

报告主题：社交网络上议题社群的公共焦虑研究

报告摘要：Although a number of researches on individual level anxiety evalua- tion have been proposed, there are few researches on evaluating the public anxiety of a social network community, which can benefit various social network analysis tasks. However, we can not simply average anxiety scales of all individuals to calculate the public anxiety score of a community, because: (1) individuals are influenced by their connections in a community, so impacts from interpersonal relations on individuals’ anxiety scales should be considered, i.e., the Structural factor; (2) public anxiety always relates to certain topics, topical discussions also reflect a community’s anxiety level, which should also be considered, i.e., the Topical factor. In this paper we initiate the study of evaluating the public anxiety of topic-based social network communities (TSNC). We propose an evaluation framework to project a TSNC’s anxiety level into a score in the [0, 1] range, using both Structural and Topical factors. We devise a cascading model to dynamically compute the anxiety score using the Structural influence. We propose a stochastic model to measure anxiety score of social network messages using a generalized user, and design a tree structure (MC-Tree) to organize messages of a TSNC to effectively compute anxiety score from the Topical factor. For large communities, computing public anxiety in real-time can be expensive, we show how to use a small sample of the community to compute the public anxiety within given confidence interval. Our model exhibits more than 80% precision and 90% recall in an empirical study on real-world data sets from Weibo.

嘉宾简介：塔娜，中国人民大学新闻学院讲师，中国人民大学新闻与社会发展研究中心研究员。2017年毕业于清华大学计算机系，获计算机科学与技术专业博士学位。研究方向为计算传播学。近年来以第一作者或通讯作者身份发表多篇CCF(中国计算机学会)A类及SCI索引论文。目前主持一项国家自然科学基金项目青年项目，及一项北京市社会科学基金项目青年项目。