ABSTRACT
Over the past decades, 360-degree virtual tours have been used to provide the public access to accurate representations of cultural heritage sites and museums. The COVID-19 pandemic has contributed to a rise in the popularity of virtual tours as a means of engaging with locations remotely and has raised an interesting question: How could we use such experiences to bring the public closer to locations that are otherwise unreachable in real life or not considered to be tourist destinations? In this study, we examine the effectiveness of promoting engagement with a city through the virtual presentation of unknown and possibly also inaccessible points of interest through a 360-degree panoramic virtual tour. The evaluation of the experience with 31 users through an online questionnaire confirms its potential to spark curiosity, promote engagement, foster reflection, and motivate users to explore the location and its attractions at their leisure, thus enabling them to experience it from their personal point of view. The outcomes highlight the need for further research to explore this potential and identify best practices for virtual experience design. © 2023 by the authors.
ABSTRACT
Recently, researchers have modeled how reliability and political bias of news may affect Facebook users' engagement, as measured using interaction metrics such as the number of shares, likes, etc. However, the temporal dynamics of Facebook users' engagement with news of varying degrees of bias and reliability is less studied. In light of the COVID-19 pandemic, it is also important to quantify how the pandemic changed user engagement with various news. This paper presents the first temporal study of Facebook users' interaction dynamics, accounting for both the bias and reliability of the publishers. We consider a dataset of 992 U.S. publishers, and the study spans the period from Jan. 2018 to July 2022. This allows us to accurately assess the effect of the covid outbreak on the temporal dynamics of Facebook users' interactions with different classes of news. Our study examines these two parameters' effect on Facebook user engagement using both per-publisher and aggregated statistics. Several findings are revealed by our analysis, including that publishers in different bias and reliability classes experienced significantly different levels of engagement dynamics during and following the covid outbreak. For example, we show that the least reliable news exhibited the most considerable growth of followers during the covid period and the most reliable news sources exhibited the greatest growth rate of followers during the post-covid period. We also show that the interaction rate (number of interactions normalized over the number of followers) with Facebook news posts during the post-covid period is smaller than it was even before the outbreak. Furthermore, we demonstrate how the COVID-19 outbreak caused statistically significant structural breaks in the temporal dynamics of engagement with several types of news, and quantify this effect. With social media becoming a popular news source during crises, the observed temporal dynamics provide important insights into how information was consumed over the recent years, benefiting both researchers and public sectors. © 2022 IEEE.
ABSTRACT
Our lives have drastically changed during the COVID-19 pandemic. Information and communications technologies (ICTs) have replaced other media as the primary means of work, communication, expression, and entertainment throughout this time. As society's reliance on technology increases throughout and possibly after the pandemic, it is critical to fully understand the multifaceted nature of engagement with technology and develop reliable instruments capable of accurately evaluating its processual nature. Therefore, this study aimed at describing and psychometrically validating a novel instrument to measure the dynamics of engagement with technology, namely the Technology Engagement Scale (TES). Data were collected from a representative sample of 2021 participants in Italy. Results from both the confirmatory analysis and the Rasch model suggested the mono-dimensionality of the 5-item TES. Moreover, empirical ordinal alpha indicated a very good internal consistency. Findings provide also solid evidence for the convergent validity of the proposed instrument. Finally, it emerged that TES levels were able to predict the frequency of online activities during the COVID-19 pandemic. Globally, these findings suggest that the TES could be considered a reliable and valid tool, able to evaluate the complex process of engagement with technology in a simple, quick, and easy-to-administer manner. [ FROM AUTHOR] Copyright of Behaviour & Information Technology is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
Misinformation is an important topic in the Information Retrieval (IR) context and has implications for both system-centered and user-centered IR. While it has been established that the performance in discerning misinformation is affected by a person's cognitive load, the variation in cognitive load in judging the veracity of news is less understood. To understand the variation in cognitive load imposed by reading news headlines related to COVID-19 claims, within the context of a fact-checking system, we conducted a within-subject, lab-based, quasi-experiment (N=40) with eye-tracking. Our results suggest that examining true claims imposed a higher cognitive load on participants when news headlines provided incorrect evidence for a claim and were inconsistent with the person's prior beliefs. In contrast, checking false claims imposed a higher cognitive load when the news headlines provided correct evidence for a claim and were consistent with the participants' prior beliefs. However, changing beliefs after examining a claim did not have a significant relationship with cognitive load while reading the news headlines. The results illustrate that reading news headlines related to true and false claims in the fact-checking context impose different levels of cognitive load. Our findings suggest that user engagement with tools for discerning misinformation needs to account for the possible variation in the mental effort involved in different information contexts. © 2023 ACM.
ABSTRACT
BACKGROUND: The COVID-19 pandemic has expanded the use of mobile health (mHealth) technologies in contact tracing, communicating COVID-19-related information, and monitoring the health conditions of the general population in the Philippines. However, the limited end-user engagement in the features and feedback along the development cycle of mHealth technologies results in risks in adoption. The World Health Organization (WHO) recommends user-centric design and development of mHealth technologies to ensure responsiveness to the needs of the end users. OBJECTIVE: The goal of the study is to understand, using end users' perspectives, the design and quality of mHealth technology implementations in the Philippines during the COVID-19 pandemic, with a focus on the areas identified by stakeholders: (1) utility, (2) technology readiness level, (3) design, (4) information, (5) usability, (6) features, and (7) security and privacy. METHODS: Using a descriptive qualitative design, we conducted 5 interviews and 3 focus group discussions (FGDs) with a total of 16 participants (6, 37.5%, males and 10, 62.5%, females). Questions were based on the Mobile App Rating Scale (MARS). Using the cyclical coding approach, transcripts were analyzed with NVivo 12. Themes were identified. RESULTS: The qualitative analysis identified 18 themes that were organized under the 7 focus areas: (1) utility: use of mHealth technologies and motivations in using mHealth; (2) technology readiness: mobile technology literacy and user segmentation; (3) design: user interface design, language and content accessibility, and technology design; (4) information: accuracy of information and use of information; (5) usability: design factors, dependency on human processes, and technical issues; (6) features: interoperability and data integration, other feature and design recommendations, and technology features and upgrades; and (7) privacy and security: trust that mHealth can secure data, lack of information, and policies. To highlight, accessibility, privacy and security, a simple interface, and integration are some of the design and quality areas that end users find important and consider in using mHealth tools. CONCLUSIONS: Engaging end users in the development and design of mHealth technologies ensures adoption and accessibility, making it a valuable tool in curbing the pandemic. The 6 principles for developers, researchers, and implementers to consider when scaling up or developing a new mHealth solution in a low-resource setting are that it should (1) be driven by value in its implementation, (2) be inclusive, (3) address users' physical and cognitive restrictions, (4) ensure privacy and security, (5) be designed in accordance with digital health systems' standards, and (6) be trusted by end users.
ABSTRACT
In this study, we focus on decrease in public activity of news media audiences on social networks and on possible media strategies of "comfortable involvement" of socially anxious people into commenting. We draw upon cognitive research that describes a vicious circle of user experience. The environment for the anxiety scenarios in relation to user comments creates favorable conditions for the growth of digital escapism. We hypothesize that: 1) Users who are looking for getting rid of anxiety on social networks are drawn into an even greater spiral of anxiety, interacting with other people in the context of news stories that provoke the whipping up of negative emotions;2) The dynamics of the cascade of messages can depend on the characteristics of the emotions embedded in the message and its context. We took 10 Russian regional media and their content on the VKontakte social network published from November 2020 to November 2021 and processed all commented posts in each media. Frequency analysis of messages demonstrated no specific pattern for anxiety. Number of comments and likes on comments correlated with specific regional issues and local news agenda more than with coronavirus agenda. Our results showed that engaged users comment more than 2 times in a period but drop out of the discussion in 2-3 moths if agenda is not escalated by news outlet itself. Emotional triggers in news stories containing reasons for anxiety depends on a combination of factors from the site's functionality to the type of news media and local information policy.
ABSTRACT
BACKGROUND: In response to the COVID-19 pandemic, Wichealth launched 4 information resources on the site's user landing dashboard page. These resources were used consistently during the period in which they were available (April 1, 2020, through October 31, 2021); however, only 9% (n=50,888) of Wichealth users eligible for inclusion in the study accessed at least one resource. User engagement with emergency response resources within the context of a web-based health educational tool has not been well investigated due to a paucity of opportunities and a lack of the ability to evaluate relevant users at scale. OBJECTIVE: This investigation was carried out to understand if user characteristics and behaviors measured by the Wichealth web-based education system are associated with a participant's motivation, or lack thereof, to engage with the added COVID-19 resources. METHODS: Sociodemographic characteristics were gathered from Wichealth users with at least one lesson completed and a complete user profile to identify which factors increase the likelihood of user access of any of the Wichealth COVID-19 response resources during the 19-month period between April 1, 2020, and October 31, 2021. A logistic regression analysis was conducted to determine the relative importance of all factors on the likelihood of a user accessing the COVID-19 resources. RESULTS: A total of 50,888 unique Wichealth users included in the study accessed the COVID-19 response resources 66,849 times during the time period. During the same period, 510,939 unique Wichealth users completed at least one lesson about how to engage in healthy behaviors with respect to parent-child feeding but did not access any COVID-19 resources. Therefore, only 9% of Wichealth users who completed a lesson during the time when COVID-19 response resources were available accessed any of the information in those resources. Users of the Spanish language Wichealth version, older users, those less educated, and users with prior Wichealth lesson engagement demonstrated the greatest likelihood of COVID-19 resource use. CONCLUSIONS: This investigation presents findings that demonstrate significant differences between Wichealth users that opted to access COVID-19-specific resources and those who chose not to during their web-based educational session. Reaching users of a web-based educational system with supplemental information may require multiple strategies to increase coverage and ensure the widest possible distribution.
ABSTRACT
Based on a quantitative content analysis of microblogs on COVID-19 that is linked to the actual Weibo user engagement (comments, reposts, and likes) they received, this study investigates the role of generic/formal frames, emotional appeals, and visual elements in people's varied levels of engagement with fake and real posts. Results revealed that relative to real posts, fake posts tended to focus more on COVID incidents that happened outside of China, utilize more episodic and human-interest frames, rely more on anger and disgust emotions, and feature more pictures. More importantly, although fake posts initially received fewer user responses than real posts, they earned significantly more reactions through employing sensational elements such as anger, conflict, and morality in their content. Most of these post-level characteristics, however, exerted minimal impact on real microblogs. Consequently, as the emotionally charged and sensationally framed fake posts drive more users to comment on and repost them, fake news may diffuse faster than real news and reach a larger audience. © 2023 Elsevier Ltd
ABSTRACT
BACKGROUND: Although government agencies acknowledge that messages about the adverse health effects of e-cigarette use should be promoted on social media, effectively delivering those health messages is challenging. Instagram is one of the most popular social media platforms among US youth and young adults, and it has been used to educate the public about the potential harm of vaping through antivaping posts. OBJECTIVE: We aim to analyze the characteristics of and user engagement with antivaping posts on Instagram to inform future message development and information delivery. METHODS: A total of 11,322 Instagram posts were collected from November 18, 2019, to January 2, 2020, by using antivaping hashtags including #novape, #novaping, #stopvaping, #dontvape, #antivaping, #quitvaping, #antivape, #stopjuuling, #dontvapeonthepizza, and #escapethevape. Among those posts, 1025 posts were randomly selected and 500 antivaping posts were further identified by hand coding. The image type, image content, and account type of antivaping posts were hand coded, the text information in the caption was explored by topic modeling, and the user engagement of each category was compared. RESULTS: Analyses found that antivaping images of the educational/warning type were the most common (253/500; 50.6%). The average likes of the educational/warning type (15 likes/post) were significantly lower than the catchphrase image type (these emphasized a slogan such as "athletesdontvape" in the image; 32.5 likes/post; P<.001). The majority of the antivaping posts contained the image content element text (n=332, 66.4%), followed by the image content element people/person (n=110, 22%). The images containing people/person elements (32.8 likes/post) had more likes than the images containing other elements (13.8-21.1 likes/post). The captions of the antivaping Instagram posts covered topics including "lung health," "teen vaping," "stop vaping," and "vaping death cases." Among the 500 antivaping Instagram posts, while most posts were from the antivaping community (n=177, 35.4%) and personal account types (n=182, 36.4%), the antivaping community account type had the highest average number of posts (1.69 posts/account). However, there was no difference in the number of likes among different account types. CONCLUSIONS: Multiple features of antivaping Instagram posts may be related to user engagement and perception. This study identified the critical elements associated with high user engagement, which could be used to design antivaping posts to deliver health-related information more efficiently.
Subject(s)
Electronic Nicotine Delivery Systems , Social Media , Vaping , Adolescent , Emotions , Humans , Young AdultABSTRACT
E-Commerce is the current day lifeline for many. After the COVID-19 pandemic the popularity of the E-Commerce increased rapidly people are now more accustomed to it. It is very important to analyze the impact of a E-Commerce web page on the customer in order to understand the customer behaviour. Where the person looks on a E commerce web page means a lot. It is challenging to analyze visual events while tracking them. Additionally, interaction patterns in significant regions of an interactive platform can be found using eye tracking data. Attention modelling for applications has become a new area of study in computer vision. Without temporal information, existing models are unable to capture the dynamic aspects of the actual attention process in free-viewing applications.To solve this problem, a solution based on an application-based saccadic model to simulate human visual dynamics while viewing applications is proposed. Eye fixes and saccades can be used to interpret a person's intention or goal in a certain circumstance. To track the user's vision, we have used pupil saccade fixation mechanism in the proposed methodology. We collect the pupil imprints based on the view, analyze the data from view samples, and recommend the optimum location to display an advertisement in any e-commerce websites. The system proves to be a better option to traditional methods as it gives 94% accuracy. © 2022 IEEE.
ABSTRACT
PurposeA lack of research has reported how playful gamification is applied to adult learners as an idea of andragogical instruction. Thus, this study aims to identify how the concept of gamification was used for adult learners in an online class during the COVID-19 pandemic and its impact on learning performance and motivation with the guidance of Knowles' andragogical principle.Design/methodology/approachThe study applied an explanatory sequential mixed method in collecting the data. Assessments' scores during the experimental research and questionnaires were used as the quantitative data. For the qualitative data, personal semi-structured interviews were employed.FindingsThe findings indicate that gamification raises student enthusiasm and interest and improves learning outcomes. Students who previously lacked attentiveness to the online class are now waiting for game quiz activities during the class meeting. Furthermore, the experimental groups reported statistically improved assessments compared to their counterparts. Indeed, some recommended other courses with whole activities of gamification and discussion rather than listening to talks.Originality/valueFor its implications, this study has enriched the literature on gamification implementation for adult learners. Regarding its originality, it has discussed an old issue of Knowles' andragogical principle from the novelty angle of gamification.
ABSTRACT
Based on a quantitative content analysis of microblogs on COVID-19 that is linked to the actual Weibo user engagement (comments, reposts, and likes) they received, this study investigates the role of generic/formal frames, emotional appeals, and visual elements in people's varied levels of engagement with fake and real posts. Results revealed that relative to real posts, fake posts tended to focus more on COVID incidents that happened outside of China, utilize more episodic and human-interest frames, rely more on anger and disgust emotions, and feature more pictures. More importantly, although fake posts initially received fewer user responses than real posts, they earned significantly more reactions through employing sensational elements such as anger, conflict, and morality in their content. Most of these post-level characteristics, however, exerted minimal impact on real microblogs. Consequently, as the emotionally charged and sensationally framed fake posts drive more users to comment on and repost them, fake news may diffuse faster than real news and reach a larger audience.
ABSTRACT
Background: Public health agencies widely adopt social media for health and risk communication. Moreover, different platforms have different affordances, which may impact the quality and nature of the messaging and how the public engages with the content. However, these platform effects are not often compared in studies of health and risk communication and not previously for the COVID-19 pandemic. Objective: This study measures the potential media effects of Twitter and Facebook on public health message design and engagement by comparing message elements and audience engagement in COVID-19-related posts by local, state, and federal public health agencies in the United States during the pandemic, to advance theories of public health messaging on social media and provide recommendations for tailored social media communication strategies. Methods: We retrieved all COVID-19-related posts from major US federal agencies related to health and infectious disease, all major state public health agencies, and selected local public health departments on Twitter and Facebook. A total of 100,785 posts related to COVID-19, from 179 different accounts of 96 agencies, were retrieved for the entire year of 2020. We adopted a framework of social media message elements to analyze the posts across Facebook and Twitter. For manual content analysis, we subsampled 1677 posts. We calculated the prevalence of various message elements across the platforms and assessed the statistical significance of differences. We also calculated and assessed the association between message elements with normalized measures of shares and likes for both Facebook and Twitter. Results: Distributions of message elements were largely similar across both sites. However, political figures (P<.001), experts (P=.01), and nonpolitical personalities (P=.01) were significantly more present on Facebook posts compared to Twitter. Infographics (P<.001), surveillance information (P<.001), and certain multimedia elements (eg, hyperlinks, P<.001) were more prevalent on Twitter. In general, Facebook posts received more (normalized) likes (0.19%) and (normalized) shares (0.22%) compared to Twitter likes (0.08%) and shares (0.05%). Elements with greater engagement on Facebook included expressives and collectives, whereas posts related to policy were more engaged with on Twitter. Science information (eg, scientific explanations) comprised 8.5% (73/851) of Facebook and 9.4% (78/826) of Twitter posts. Correctives of misinformation only appeared in 1.2% (11/851) of Facebook and 1.4% (12/826) of Twitter posts. Conclusions: In general, we find a data and policy orientation for Twitter messages and users and a local and personal orientation for Facebook, although also many similarities across platforms. Message elements that impact engagement are similar across platforms but with some notable distinctions. This study provides novel evidence for differences in COVID-19 public health messaging across social media sites, advancing knowledge of public health communication on social media and recommendations for health and risk communication strategies on these online platforms.
ABSTRACT
Due to the lockdown, more and more people are used to communicating with AI voice assistants during the post-COVID era. This study investigates the relationship between the perceived cuteness of AI voice assistants and the intention to purchase via a moderated serial-mediation model. We tested a PLS-SEM model with 284 survey data from an online experiment. The findings indicate that: (1) different cuteness appearances lead to different levels of perceived cuteness; (2) perceived cuteness positively affects intention to purchase; (3) the positive direct effect is serial mediated by social presence and user engagement; (4) the serial mediation effect is negatively moderated by perceived risk of service failure, which means the positive influence of perceived cuteness on intention to purchase is weakened at a high level of perceived risk. Our research has both theoretical and managerial contributions, which also reminds enterprises to grasp the cuteness degree of the product.
ABSTRACT
Public displays are some of the most challenging interfaces to design because of two key characteristics. First, the experience should be engaging, to attract and maintain users' attention. Second, the interaction with the display should be natural, meaning that users should be able to receive the desired output with little or no training. Holographic displays are increasingly popular in public spaces such as museums and concert halls but there is little published research on users' experiences with such displays. Previous research has suggested both tangible and intangible inputs as engaging and natural options for holographic displays, but there is no conclusive evidence on their relative merits. Hence, we run a study to investigate the user experience with a holographic display comparing the level of engagement and feeling of natural experience in the interacting process. We used a mix of surveys, interviews, video recordings, and task-based metrics to measure users' performance on a specific task, the perceived usability, and levels of engagement and satisfaction. Our findings suggest that a tangible input was reported as more natural than the intangible one, however, both tangible and intangible inputs were found to be equally engaging. The latter findings contribute to the efforts of designing intangible public holographic displays and other interactive systems that take into consideration health safety issues, especially during the Covid-19 pandemic era in which contamination can be established with tangible and physical interaction between users and public displays, yet without affecting the level of engagement compared to the tangible experience. © 2022 IEEE.
ABSTRACT
This study assesses the online societal association of leaders and healthcare organizations from the top-10 COVID-19 resilient nations through public engagement, sentiment strength, and inclusivity and diversity strength. After analyzing 173,071 Tweets authored by the leaders and health organizations, our findings indicate that United Arab Emirate's Prime Minister had the highest online societal association (normalized online societal association: 1.000) followed by the leaders of Canada and Turkey (normalized online societal association: 0.068 and 0.033, respectively); and among the healthcare organizations, the Public Health Agency of Canada was the most impactful (normalized online societal association: 1.000) followed by the healthcare agencies of Turkey and Spain (normalized online societal association: 0.632 and 0.094 respectively). In comparison to healthcare organizations, the leaders displayed a strong awareness of individual factors and generalized their Tweets to a broader audience. The findings also suggest that users prefer accessing social media platforms for information during health emergencies and that leaders and healthcare institutions should realize the potential to use them effectively.
ABSTRACT
The COVID-19 pandemic led governments to rely on the versatility of social media to communicate with their citizens. This paper analyzes the Facebook communication of political leaders and health departments from 17 countries during the COVID-19 pandemic. We evaluate the citizen's response under the frameworks of media richness and user engagement. We note that governments and leaders communicate primarily through richer media (photos and videos), despite a negative correlation between media richness and user engagement. Plain-Text messages posted by country leaders attract the most engagement, while their COVID-19 communication tends to generate lower engagement. On the other hand, health departments' pages experienced a sharp increase in engagement around COVID-19 communication as citizens sought information during the pandemic. Finally, topical analysis shows that Discussions and Co-Use of COVID-19 with other topics can boost citizens' engagement. Our comparative analysis shows practical implications for social media users and social media designers. Our findings can help governments and organizations design effective social media communication during crises. © 2022 ACM.
ABSTRACT
Background: The COVID-19 pandemic has generated an infodemic, an overabundance of online and offline information. In this context, accurate information as well as misinformation and disinformation about the links between nutrition and COVID-19 have circulated on Twitter since the onset of the pandemic. Objective: The purpose of this study was to compare tweets on nutrition in times of COVID-19 published by 2 groups, namely, a preidentified group of dietitians and a group of general users of Twitter, in terms of themes, content accuracy, use of behavior change factors, and user engagement, in order to contrast their information sharing behaviors during the pandemic. Methods: Public English-language tweets published between December 31, 2019, and December 31, 2020, by 625 dietitians from Canada and the United States, and Twitter users were collected using hashtags and keywords related to nutrition and COVID-19. After filtration, tweets were coded against an original codebook of themes and the Theoretical Domains Framework (TDF) for identifying behavior change factors, and were compared to reliable nutritional recommendations pertaining to COVID-19. The numbers of likes, replies, and retweets per tweet were also collected to determine user engagement. Results: In total, 2886 tweets (dietitians, n=1417; public, n=1469) were included in the analyses. Differences in frequency between groups were found in 11 out of 15 themes. Grocery (271/1417, 19.1%), and diets and dietary patterns (n=507, 34.5%) were the most frequently addressed themes by dietitians and the public, respectively. For 9 out of 14 TDF domains, there were differences in the frequency of usage between groups. "Skills" was the most used domain by both groups, although they used it in different proportions (dietitians: 612/1417, 43.2% vs public: 529/1469, 36.0%; P<.001). A higher proportion of dietitians' tweets were accurate compared with the public's tweets (532/575, 92.5% vs 250/382, 65.5%; P<.001). The results for user engagement were mixed. While engagement by likes varied between groups according to the theme, engagement by replies and retweets was similar across themes but varied according to the group. Conclusions: Differences in tweets between groups, notably ones related to content accuracy, themes, and engagement in the form of likes, shed light on potentially useful and relevant elements to include in timely social media interventions aiming at fighting the COVID-19-related infodemic or future infodemics.
ABSTRACT
A service (social) robot is defined as the Internet of Things (IoT) consisting of a physical robot body that connects to one or more Cloud services to facilitate human-machine interaction activities to enhance the functionality of a traditional robot. Many studies found that anthropomorphic designs in robots resulted in greater user engagement. Humanoid service robots usually behave like natural social interaction partners for human users, with emotional features such as speech, gestures, and eye-gaze, referring to the users’ cultural and social background. During the COVID-19 pandemic, service robots play a much more critical role in helping to safeguard people in many countries nowadays. This paper gives an overview of the research issues from technical and social-technical perspectives, especially in Human-Robot Interaction (HRI), emotional expression, and cybersecurity issues, with a case study of gamification and service robots. © 2022, Springer Nature Switzerland AG.
ABSTRACT
BACKGROUND: Social media platforms (SMPs) are frequently used by various pharmaceutical companies, public health agencies, and nongovernment organizations (NGOs) for communicating health concerns, new advancements, and potential outbreaks. Although the benefits of using them as a tool have been extensively discussed, the online activity of various health care organizations on SMPs during COVID-19 in terms of engagement and sentiment forecasting has not been thoroughly investigated. OBJECTIVE: The purpose of this research is to analyze the nature of information shared on Twitter, understand the public engagement generated on it, and forecast the sentiment score for various organizations. METHODS: Data were collected from the Twitter handles of 5 pharmaceutical companies, 10 US and Canadian public health agencies, and the World Health Organization (WHO) from January 1, 2017, to December 31, 2021. A total of 181,469 tweets were divided into 2 phases for the analysis, before COVID-19 and during COVID-19, based on the confirmation of the first COVID-19 community transmission case in North America on February 26, 2020. We conducted content analysis to generate health-related topics using natural language processing (NLP)-based topic-modeling techniques, analyzed public engagement on Twitter, and performed sentiment forecasting using 16 univariate moving-average and machine learning (ML) models to understand the correlation between public opinion and tweet contents. RESULTS: We utilized the topics modeled from the tweets authored by the health care organizations chosen for our analysis using nonnegative matrix factorization (NMF): cumass=-3.6530 and -3.7944 before and during COVID-19, respectively. The topics were chronic diseases, health research, community health care, medical trials, COVID-19, vaccination, nutrition and well-being, and mental health. In terms of user impact, WHO (user impact=4171.24) had the highest impact overall, followed by public health agencies, the Centers for Disease Control and Prevention (CDC; user impact=2895.87), and the National Institutes of Health (NIH; user impact=891.06). Among pharmaceutical companies, Pfizer's user impact was the highest at 97.79. Furthermore, for sentiment forecasting, autoregressive integrated moving average (ARIMA) and seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) models performed best on the majority of the subsets of data (divided as per the health care organization and period), with the mean absolute error (MAE) between 0.027 and 0.084, the mean square error (MSE) between 0.001 and 0.011, and the root-mean-square error (RMSE) between 0.031 and 0.105. CONCLUSIONS: Our findings indicate that people engage more on topics such as COVID-19 than medical trials and customer experience. In addition, there are notable differences in the user engagement levels across organizations. Global organizations, such as WHO, show wide variations in engagement levels over time. The sentiment forecasting method discussed presents a way for organizations to structure their future content to ensure maximum user engagement.