A large-scale analysis of diurnal and seasonal mood cycles in global social networks has been performed successfully over the past ten years using Twitter, Facebook and blogs. This study describes the application of remote biometric technologies to such investigations on a large scale for the first time. The performance of this research was under real conditions producing results that conform to natural human diurnal and seasonal rhythm patterns. The derived results of this, 208 million data research on diurnal emotions, valence and facial temperature correlate with the results of an analogical Twitter research performed worldwide (UK, Australia, US, Canada, Latin America, North America, Europe, Oceania, and Asia). It is established that diurnal valence and sadness were correlated with one another both prior to and during the period of the coronavirus crisis, and that there are statistically significant relationships between the values of diurnal happiness, sadness, valence and facial temperature and the numbers of their data. Results from the simulation and formal comparisons appear in this article. Additionally the analyses on the COVID-19 screening, diagnosing, monitoring and analyzing by applying biometric and AI technologies are described in Housing COVID-19 Video Neuroanalytics.

在过去十年中，已经使用Twitter，Facebook和博客成功地对全球社交网络中的每日和季节性情绪周期进行了大规模分析。这项研究首次描述了远程生物识别技术在此类研究中的应用。这项研究的执行是在真实条件下产生的结果符合人类自然昼夜节律模式。这项基于2.08亿项关于日间情绪，化合价和面部温度的数据研究的派生结果与全球范围内（英国，澳大利亚，美国，加拿大，拉丁美洲，北美，欧洲，大洋洲和亚洲）进行的Twitter类推研究的结果相关）。可以确定，冠状病毒危机发生之前和期间，日价和悲伤之间相互关联，并且日间幸福，悲伤，价和面部温度的数值与其数量之间存在统计学上的显着关系。数据。模拟和形式比较的结果出现在本文中。此外，《房屋COVID-19视频神经分析》中介绍了通过应用生物识别技术和AI技术对COVID-19进行筛选，诊断，监测和分析的分析。