Background: The coronavirus disease (COVID-19) pandemic presents one of the most challenging global crises at the dawn of a new decade. Public health authorities (PHAs) are increasingly adopting the use of social media such as Facebook to rapidly communicate and disseminate pandemic response measures to the public. Understanding of communication strategies across different PHAs and examining the public response on the social media landscapes can help improve practices for disseminating information to the public. Objective: This study aims to examine COVID-19-related outreach efforts of PHAs in Singapore, the United States, and England, and the corresponding public response to these outreach efforts on Facebook. Methods: Posts and comments from the Facebook pages of the Ministry of Health (MOH) in Singapore, the Centers for Disease Control and Prevention (CDC) in the United States, and Public Health England (PHE) in England were extracted from January 1, 2019, to March 18, 2020. Posts published before January 1, 2020, were categorized as pre-COVID-19, while the remaining posts were categorized as peri-COVID-19 posts. COVID-19-related posts were identified and classified into themes. Metrics used for measuring outreach and engagement were frequency, mean posts per day (PPD), mean reactions per post, mean shares per post, and mean comments per post. Responses to the COVID-19 posts were measured using frequency, mean sentiment polarity, positive to negative sentiments ratio (PNSR), and positive to negative emotions ratio (PNER). Toxicity in comments were identified and analyzed using frequency, mean likes per toxic comment, and mean replies per toxic comment. Trend analysis was performed to examine how the metrics varied with key events such as when COVID-19 was declared a pandemic. Results: The MOH published more COVID-19 posts (n=271; mean PPD 5.0) compared to the CDC (n=94; mean PPD 2.2) and PHE (n=45; mean PPD 1.4). The mean number of comments per COVID-19 post was highest for the CDC (mean CPP 255.3) compared to the MOH (mean CPP 15.6) and PHE (mean CPP 12.5). Six major themes were identified, with posts about prevention and safety measures and situation updates being prevalent across the three PHAs. The themes of the MOH’s posts were diverse, while the CDC and PHE posts focused on a few themes. Overall, response sentiments for the MOH posts (PNSR 0.94) were more favorable compared to response sentiments for the CDC (PNSR 0.57) and PHE (PNSR 0.55) posts. Toxic comments were rare (0.01%) across all PHAs. Conclusions: PHAs’ extent of Facebook use for outreach purposes during the COVID-19 pandemic varied among the three PHAs, highlighting the strategies and approaches that other PHAs can potentially adopt. Our study showed that social media analysis was capable of providing insights about the communication strategies of PHAs during disease outbreaks.

Background: Public health authorities have been recommending interventions such as physical distancing and face masks, to curtail the transmission of coronavirus disease (COVID-19) within the community. Public perceptions toward such interventions should be identified to enable public health authorities to effectively address valid concerns. The Health Belief Model (HBM) has been used to characterize user-generated content from social media during previous outbreaks, with the aim of understanding the health behaviors of the public. Objective: This study is aimed at developing and evaluating deep learning–based text classification models for classifying social media content posted during the COVID-19 outbreak, using the four key constructs of the HBM. We will specifically focus on content related to the physical distancing interventions put forth by public health authorities. We intend to test the model with a real-world case study. Methods: The data set for this study was prepared by analyzing Facebook comments that were posted by the public in response to the COVID-19–related posts of three public health authorities: the Ministry of Health of Singapore (MOH), the Centers for Disease Control and Prevention, and Public Health England. The comments made in the context of physical distancing were manually classified with a Yes/No flag for each of the four HBM constructs: perceived severity, perceived susceptibility, perceived barriers, and perceived benefits. Using a curated data set of 16,752 comments, gated recurrent unit–based recurrent neural network models were trained and validated for text classification. Accuracy and binary cross-entropy loss were used to evaluate the model. Specificity, sensitivity, and balanced accuracy were used to evaluate the classification results in the MOH case study. Results: The HBM text classification models achieved mean accuracy rates of 0.92, 0.95, 0.91, and 0.94 for the constructs of perceived susceptibility, perceived severity, perceived benefits, and perceived barriers, respectively. In the case study with MOH Facebook comments, specificity was above 96% for all HBM constructs. Sensitivity was 94.3% and 90.9% for perceived severity and perceived benefits, respectively. In addition, sensitivity was 79.6% and 81.5% for perceived susceptibility and perceived barriers, respectively. The classification models were able to accurately predict trends in the prevalence of the constructs for the time period examined in the case study. Conclusions: The deep learning–based text classifiers developed in this study help to determine public perceptions toward physical distancing, using the four key constructs of HBM. Health officials can make use of the classification model to characterize the health behaviors of the public through the lens of social media. In future studies, we intend to extend the model to study public perceptions of other important interventions by public health authorities.

Empathy is a vital factor that contributes to mutual understanding, and joint problem-solving. In recent years, a growing number of studies have recognized the benefits of empathy and started to incorporate empathy in conversational systems. We refer to this topic as empathetic conversational systems. To identify the critical gaps and future opportunities in this topic, this paper examines this rapidly growing field using five review dimensions: (i) conceptual empathy models and frameworks, (ii) adopted empathy-related concepts, (iii) datasets and algorithmic techniques developed, (iv) evaluation strategies, and (v) state-of-the-art approaches. The findings show that most studies have centered on the use of the EMPATHETICDIALOGUES dataset, and the text-based modality dominates research in this field. Studies mainly focused on extracting features from the messages of the users and the conversational systems, with minimal emphasis on user modeling and profiling. Notably, studies that have incorporated emotion causes, external knowledge, and affect matching in the response generation models, have obtained significantly better results. For implementation in diverse real-world settings, we recommend that future studies should address key gaps in areas of detecting and authenticating emotions at the entity level, handling multimodal inputs, displaying more nuanced empathetic behaviors, and encompassing additional dialogue system features.

BACKGROUND: The behavior of medication nonadherence is distinguished into primary and secondary nonadherence. Primary nonadherence (PNA) is not as thoroughly studied as secondary nonadherence. OBJECTIVE: To explore and synthesize contributing factors to PNA based on the existing body of literature. METHODS: A search was performed on the PubMed, PsycINFO, CINAHL, and ScienceDirect databases to identify previously published scholarly articles that described the “factors,” “reasons,” “determinants” or “facilitators” of PNA. The alternate spelling of “nonadherence” was used as well. The effect that the articles had in the research community, as well as across social media, was also explored. RESULTS: 22 studies met the inclusion criteria for this review. The PNA factors that the studies identified were diverse, spanning economic, social, and medical dimensions. A multilevel classification method was applied to categorize the factors into 5 broad groups—patient, medication, health care provider, health care sy...