GIONet: Global information optimized network for multi-center COVID-19 diagnosis via COVID-GAN and domain adversarial strategy.

The outbreak of coronavirus disease (COVID-19) in 2019 has highlighted the need for automatic diagnosis of the disease, which can develop rapidly into a severe condition. Nevertheless, distinguishing between COVID-19 pneumonia and community-acquired pneumonia (CAP) through computed tomography scans can be challenging due to their similar characteristics. The existing methods often perform poorly in the 3-class classification task of healthy, CAP, and COVID-19 pneumonia, and they have poor ability to handle the heterogeneity of multi-centers data. To address these challenges, we design a COVID-19 classification model using global information optimized network (GIONet) and cross-centers domain adversarial learning strategy. Our approach includes proposing a 3D convolutional neural network with graph enhanced aggregation unit and multi-scale self-attention fusion unit to improve the global feature extraction capability. We also verified that domain adversarial training can effectively reduce feature distance between different centers to address the heterogeneity of multi-center data, and used specialized generative adversarial networks to balance data distribution and improve diagnostic performance. Our experiments demonstrate satisfying diagnosis results, with a mixed dataset accuracy of 99.17% and cross-centers task accuracies of 86.73% and 89.61%.

Consumer brand engagement on social media in the COVID-19 pandemic: the roles of country-of-origin and consumer animosity: An International Journal

PurposeThe coronavirus disease (COVID-19) pandemic unprecedentedly shocks the market. Little is known about the impact of COVID-19 on brand engagement across country-of-origin (COO) and country-of-market (COM). To address the gap, this study examines how the spread of the COVID-19 affects consumer brand engagement on social media for global brands through the mechanisms of the COO and consumer animosity.Design/methodology/approachThe authors collect consumer engagement activity data from Facebook for eight global smartphone brands and match it with the COVID-19 statistics. Ordinary least square (OLS) models are used to estimate the impact on global brands brought by the spread of the COVID-19.FindingsThe results show that consumer brand engagement decreases for all brands in a COM as the number of confirmed COVID-19 new cases increases in the COM. Consumer brand engagement decreases for a brand across all COM as the number of confirmed COVID-19 new cases increases in the brand’s COO. If a brand’s COO is imputed for the pandemic, its consumer brand engagement will receive additional negative impacts across all COM.Originality/valueThis study enriches the COO literature by showing how the spread of a pandemic affects consumer brand engagement via COO and discovers the moderating role of consumer animosity.