We present a computational approach for estimating emotion contagion on social media networks. Built on a foundation of psychology literature, our approach estimates the degree to which the perceivers' emotional states (positive or negative) start to match those of the expressors, based on the latter's content. We use a combination of deep learning and social network analysis to model emotion contagion as a diffusion process in dynamic social network graphs, taking into consideration key aspects like causality, homophily, and interference. We evaluate our approach on user behavior data obtained from a popular social media platform for sharing short videos. We analyze the behavior of 48 users over a span of 8 weeks (over 200k audio-visual short posts analyzed) and estimate how contagious the users with whom they engage with are on social media. As per the theory of diffusion, we account for the videos a user watches during this time (inflow) and the daily engagements; liking, sharing, downloading or creating new videos (outflow) to estimate contagion. To validate our approach and analysis, we obtain human feedback on these 48 social media platform users with an online study by collecting responses of about 150 participants. We report users who interact with more number of creators on the platform are 12% less prone to contagion, and those who consume more content of `negative' sentiment are 23% more prone to contagion. We will publicly release our code upon acceptance.
翻译:我们提出一种计算方法来估计社交媒体网络中的情感传染。基于心理学文献,我们的方法根据心理学文献,估计感知者情感状态(积极或消极)开始与表达者情感状态(积极或消极)相匹配的程度,以后者的内容为基础。我们使用深层次的学习和社会网络分析结合,在动态社交网络图表中将情感传染模拟为传播过程,同时考虑到因果关系、同质和干扰等关键方面;我们评估从广受欢迎的社交媒体平台获取的用户行为数据,以分享短视频。我们分析了48个用户在8周内的行为(分析超过200公里的视听短片),并估计了他们与之打交道的用户在社交媒体上的传染程度。根据传播理论,我们考虑到动态社交网络图表中用户观看的视频;欢迎、分享、下载或创建新的视频(流出),以估计传染性。为了验证我们的做法和分析,我们从这些48个社交媒体平台用户获得人的反馈,通过收集大约150名参与者的答复(分析),并估计他们参与社交媒体的用户在社交媒体媒体媒体上的行为。根据传播理论,我们报告在这一时期(流化程度更低的用户将接受率)到更低的23的用户将更易被接受者。