Twitter中的情绪传染现象

发布时间：2018-08-24 10:46

【摘要】：在Twitter中是否存在情绪传染现象是社会科学中一个待解决的问题。首先通过LIWC2007获取了包含106 641个用户的Tw itter社交网络中所有用户的情绪时间序列,然后采用一系列的单位根检验证明了相关时间序列的平稳性,通过格兰杰因果检验,在预测用户情绪值的回归式中加入了用户关注好友过去时间的情绪值作为自变量,并采用统计假设检验的方法证明了该自变量的系数不为0,从而说明了用户的情绪会显著地被其关注好友过去的情绪所影响,即用户关注好友的情绪是用户情绪的格兰杰原因。用同样的方法证明了用户情绪并不是用户关注好友情绪的格兰杰原因,由于社交选择现象是一种双向关系,所以该结果是由情绪传染现象造成的。此外,通过统计分析发现Twitter中绝大部分单向关注好友都是非熟人,而绝大部分双向关注好友都是熟人。格兰杰因果检验的结果说明了人们的情绪既会被熟人的情绪所传染,也会被非熟人的情绪所传染。
[Abstract]:The existence of emotional contagion in Twitter is a problem to be solved in social science. First, the emotional time series of all users in Tw itter social network including 106,641 users were obtained by LIWC2007. Then, a series of unit root tests were used to prove the smoothness of the related time series, and the Granger causality test was used. In the regression formula for predicting the user's emotional value, the user's emotional value of paying attention to the past time of the friend was added as an independent variable. The statistical hypothesis test is used to prove that the coefficient of the independent variable is not 0, which shows that the user's emotion will be significantly affected by his concern about the past emotions of his friends, that is, the user's concern for his friends is the Granger cause of user's emotion. The same method is used to prove that user emotion is not the Granger reason why users pay attention to their friends' emotions. Because the phenomenon of social choice is a two-way relationship, the result is caused by the phenomenon of emotional contagion. In addition, through the statistical analysis, it is found that most of the one-way friends in Twitter are non-acquaintances, while the majority of two-way attention friends are acquaintances. The result of Granger causality test shows that people's emotions can be infected by both familiar and unknown emotions.
【作者单位】：福州大学数学与计算机科学学院;
【基金】：国家自然科学基金青年项目(61300105) 教育部博士点基金联合资助项目(2012351410010) 福建省科技重大专项项目(2013H6012) 福州市科技计划项目(2012-G-113,2013-PT-45)
【分类号】：G206;B842.6

【相似文献】