Introduction/context: Healthcare workers (HCWs) play an important role in fighting against the COVID-19 pandemic. However, they have been exposed to mixed public responses more significantly during the COVID-19 pandemic, which have potentially affected their work and life.Aim: We aim to study what public responses toward HCWs existed, how and why such public responses impacted HCW’s work engagement and well-being, and how Human Resource (HR) professionals navigate these impacts. These understandings are important for improving HCWs’ work and life quality.Methods: We adopted a mixed approach including both quantitative and qualitative methods to investigate how the public responses impact HCWs’ work engagement and well-being and how human resource management (HRM) shall intervene. Our quantitative study enables us to collect and analyze a large amount of public responses toward HCWs from the social media platform during the COVID-19 pandemic globally, and uncover the sentiments and topics of these pubic responses via big data and AI technologies. Our qualitative study allows us to understand how and why these public responses impact HCWs’ work engagement and well-being via interviews and further identify how HR professionals shall navigate these impacts.Results: The sentiment analysis showed that 55.9% of the discussions toward HCWs were positive, 27.2% were neutral, and 16.9% were negative. The topic modeling analysis indicated that the commonly identified topics were related to fear (the negative responses) and gratitude (the positive responses). The interviews with 18 HCWs revealed that HCWs’ work engagement and well-being were decreased by negative public responses through experiencing tension or disappointment due to social and physical ostracism, rejection, discrimination, and criticism. On the other hand, positive public responses in terms of encouragement, recognition, and tangible donations increased their work engagement and well-being. The analysis also suggested that occupational calling served as a mechanism that explained why public responses had such impacts on HCWs. The interview results also highlighted the significance of HRM in bridging positive public responses toward HCWs and revealed problems with communication from HRM during the pandemic. This research provides practical implications about how to improve HCWs work engagement and well-being during the pandemic via public and HRM efforts.

In recent research, supervised image clustering based on Graph Neural Networks (GNN) connectivity prediction has demonstrated considerable improvements over traditional clustering algorithms. However, existing supervised image clustering algorithms are usually time-consuming and limit their applications. In order to infer the connectivity between image instances, they usually created a subgraph for each image instance. Due to the creation and process of a large number of subgraphs as the input of GNN, the computation overheads are enormous. To address the high computation overhead problem in the GNN connectivity prediction, we present a time-efficient and effective GNN-based supervised clustering framework based on density division namely DDC-GNN. DDC-GNN divides all image instances into high-density parts and low-density parts, and only performs GNN subgraph connectivity prediction on the low-density parts, resulting in a significant reduction in redundant calculations. We test two typical models in the GNN connectivity prediction module in the DDC-GNN framework, which are the graph convolutional networks (GCN)-based model and the graph auto-encoder (GAE)-based model. Meanwhile, adaptive subgraphs are generated to ensure sufficient contextual information extraction for low-density parts instead of the fixed-size subgraphs. According to the experiments on different datasets, DDC-GNN achieves higher accuracy and is almost five times quicker than those without the density division strategy.

During the COVID-19 pandemic, nations implemented various preventive measures, triggering varying online responses. This study examines cultural influences on public online stances toward these measures and their impacts on COVID-19 cases/deaths. Stance detection analysis was used to analyze 16,428,557 Tweets regarding COVID-19 preventive measures from 95 countries, selected based on Hofstede 's cultural dimensions. To ensure the variety of population, countries were chosen based on Twitter data availability and a minimum sample size of 385 tweets, achieving a 95% confidence level with a 5% margin of error. The weighted regression analysis revealed that the relationship between culture and online stances depends on the cultural congruence of each measure. Specifically, power distance positively predicted stances for all measures, while indulgence had a negative effect overall. Effects of other cultural indices varied across measures. Individualism negatively affected face coverings stances. Uncertainty avoidance influenced lockdown and vaccination stances negatively but had a positive effect on social distancing stances. Long-term orientation negatively affected lockdown and social distancing stances but positively influenced quarantine stances. Cultural tightness only negatively affected face coverings and quarantine stances. Online stances toward face coverings mediated the relationship between cultural indices and COVID-19 cases/deaths. As such, public health officials should consider cultural profiles and use culturally congruent communication strategies when implementing preventive measures for future pandemics. Furthermore, leveraging digital tools is vital in navigating and shaping online stances to enhance the effectiveness of these measures.