Health, Psychosocial, and Social issues emanating from COVID-19 pandemic based on Social Media Comments using Natural Language Processing

The COVID-19 pandemic has caused a global health crisis that affects many aspects of human lives. In the absence of vaccines and antivirals, several behavioural change and policy initiatives, such as physical distancing, have been implemented to control the spread of the coronavirus. Social media data can reveal public perceptions toward how governments and health agencies across the globe are handling the pandemic, as well as the impact of the disease on people regardless of their geographic locations in line with various factors that hinder or facilitate the efforts to control the spread of the pandemic globally. This paper aims to investigate the impact of the COVID-19 pandemic on people globally using social media data. We apply natural language processing (NLP) and thematic analysis to understand public opinions, experiences, and issues with respect to the COVID-19 pandemic using social media data. First, we collect over 47 million COVID-19-related comments from Twitter, Facebook, YouTube, and three online discussion forums. Second, we perform data preprocessing which involves applying NLP techniques to clean and prepare the data for automated theme extraction. Third, we apply context-aware NLP approach to extract meaningful keyphrases or themes from over 1 million randomly selected comments, as well as compute sentiment scores for each theme and assign sentiment polarity based on the scores using lexicon-based technique. Fourth, we categorize related themes into broader themes. A total of 34 negative themes emerged, out of which 15 are health-related issues, psychosocial issues, and social issues related to the COVID-19 pandemic from the public perspective. In addition, 20 positive themes emerged from our results. Finally, we recommend interventions that can help address the negative issues based on the positive themes and other remedial ideas rooted in research.

lockdowns (and other restrictive measures) imposed by governments and public health agencies to curtail the spread of the virus. Evidence has already shown that emerging infectious diseases impose significant burden on global economies and public health [3,[11][12][13]. To understand public concern and personal experiences, and factors that hinder or facilitate the efforts to control the spread of the COVID-19 pandemic globally, social media data can produce rich and useful insights that were previously impossible in both scale and extent [14].
Over the years, social media has witnessed a surge in active users to more than 3.8 billion globally [15], making it a rich source of data for research in diverse domains. In the health domain, social media data (i.e., user comments or posts on Twitter, Facebook, YouTube, Instagram, online forums, blogs, etc.) have been used to investigate mental health issues [16,17], maternal health issues [18,19], diseases [20][21][22][23][24], substance use [25,26] and other health-related issues [27,28]. Other domains (e.g., politics, commerce, marketing, banking) have also witnessed widespread use of social media data to uncover new insights related to election results [29][30][31][32], election campaign [33], customer behaviour and engagement [34,35], etc. As regards the COVID-19 crisis, social media data can reveal public perceptions toward how governments and health agencies across the globe are handling the pandemic, as well as the social, economic, psychological, and healthrelated impact of the disease on people regardless of their geographic locations in line with various factors that hinder or facilitate the efforts to control the spread of the COVID-19 pandemic globally.
In this paper, we apply natural language processing (NLP) to understand public opinions, experiences, and issues with respect to the COVID-19 pandemic using data from Twitter, Facebook, YouTube, and three online discussion forums (i.e., Archinect.com [36,37], LiveScience.com [38], and PushSquare.com [39]). NLP is a well-established method that has been applied in many health informatics papers to understand various health-related issues. For example, Abdalla et al. studied the privacy implications of word embeddings trained on clinical data containing personal health information [40], while Bekhuis et al. applied NLP to extract clinical phrases and keywords from corpus of messages posted to an internet mailing list [41].
The contributions of our research are as follows: 1. We apply a context-aware Natural Language Processing (NLP) approach for extracting opinionated themes from COVID-19-related social media comments.
2. We uncover various negative and positive themes representing public perceptions toward the COVID-19 pandemic. Our results reveal 34 negative themes, out of which 15 are health-related issues, psychosocial issues, and social issues related to the pandemic from the public perspective. In addition, 20 positive themes emerged from our results. 3. We recommend interventions that can help address the health, psychosocial, and social issues based on the positive themes and other remedial ideas rooted in research. These interventions will help governments, health professionals and agencies, institutions, and individuals in their efforts to curb the spread of COVID-19 and minimize its impact, as well as in reacting to any future pandemics.

Relevant Literature
Social media has been a rich source of data for research in many domains, including health [42]. Research that utilizes social media in conjunction with natural language processing (NLP) within the health domain continues to grow and cover broad application areas such as health surveillance (e.g., mental health, substance use, diseases, pharmacovigilance, etc.), health communication, sentiment analysis, and so on [43]. For example, Park et al. [44] used the lexicon-based approach to track prevalence of keywords indicating public interest in four health issues -Ebola, ecigarette, marijuana, and influenza -based on social media data. Afterwards, they generated topics or themes that explain changes in discussion volume over time using the Latent Dirichlet Allocation (LDA) algorithm. Similarly, Jelodar et al. [45] applied LDA to extract latent topics in COVID-19-related comments and used the LSTM recurrent neural network technique for sentiment classification. Furthermore, Nobles et al. [46] used social media data to examine the needs (including seeking health information) of reportable sexually transmitted diseases community. Their NLP approach involves extracting top 50 unigrams from the posts based on frequency, and then generating topics or themes using the non-negative matrix factorization technique instead of LDA. Paul et al. [47] applied the Ailment Topic Aspect Model to generate latent topics from Twitter data with the aim of detecting mentions of specific ailments, including allergies, obesity, and insomnia. They used a list of keyphrases to automatically identify possible systems and treatments. McNeill et al. [48] investigated how the dissemination of H1N1-related advice in the United Kingdom encourages/discourages vaccine and antiviral uptake using Twitter data. They conducted an automated content analysis using KH-Coder tool to explore potential topics based on frequency of occurrence, and then performed a more detailed or conversational analysis to understand skepticism over economic beneficiaries of vaccination, as well as the risks and benefits of medication based on public opinion. On the other hand, Oyebode et al. [49] performed sentiment analysis on user reviews of mental health apps using machine learning approach. They compared five classifiers (based on five different machine learning algorithms) and used the best performing classifier to predict the sentiment polarity of reviews. However, none of the approaches above considers the context in which words appear in unstructured texts, which instinctively plays a huge role in conveying meaning.
To investigate the significance of contextual text analysis, Dave et al. [50] compared the non-contextual N-Gram Chunking approach and the contextual Part-of-Speech (POS) chunking approach in their experimental research in the field of advertising. While the N-Gram chunking method simply extracts words of varying lengths within sentence boundary as candidate keyphrases or themes, the POS chunking method infers the context of words using POS patterns such as one or more noun tags (NN, NNP, NNS, and NNPS) along with adjective tags (JJ) and optional cardinal tags (CD) and determiners (DT). They focus on keyphrases of up to length six for their experiments. Their initial assessment showed that majority of the keyphrases generated using the N-Gram chunking method are not meaningful within the advertising context, hence not useful. Furthermore, they observed the impact of keyphrases from both methods on the performance of classification systems based on Naïve Bayes, logistic regression, and bagging machine learning algorithms. Their findings revealed that systems using the POS chunking method outperformed those using the N-Gram chunking method for feature extraction. We leveraged Dave et al.'s contextual method in this work and extended it to capture additional POS patterns, NLP preprocessing techniques, and sentiment scoring using lexicon-based technique.
Finally, to uncover insights about the type of information shared on Twitter during the peak of the H1N1 (swine flu) pandemic in 2009, Ahmed et al. [51] generated eight broad themes using coding method involving expert reviewers. Similarly, Bekhuis et al. [41] involved two dentists to manually and iteratively classify clinical phrases into categories and subcategories. We also used this method in the theme categorization stage of our work to group related themes or keyphrases into broad themes.

Methods
The main goal of this paper is to understand people's personal experiences and opinions with respect to the COVID-19 pandemic using social media data. To achieve this, we apply various standard and well-known computational techniques which are highlighted below and summarized in Figure 1.  After the preprocessing tasks were completed, non-English and duplicated comments were removed, thereby reducing total number of comments to 8,021,341.

Theme Extraction
Next, we randomly selected 1,051,616 comments (representing approximately 13% of the entire dataset) and then extracted meaningful keyphrases or themes that convey the topical content of the comments. We refer to the dataset containing the comments as corpus and each comment as document in the remaining parts of this paper. We focus on themes that are opinionated (i.e., express or imply positive or negative sentiment [56]) since our goal is to determine public opinions and impact with respect to the COVID-19 pandemic. We extracted candidate themes from our corpus using a seven-stage context-aware NLP approach, shown in Figure 2. We implemented our approach using the Python programming language.

Grammar definition
A grammar is a set of rules that describe how syntactic units (such as sentences and phrases) should be deconstructed into their constituents [57]. To derive meaningful themes or keyphrases, we defined a grammar (see below) which specifies a meaningful part-of-speech (POS) pattern that the syntactic parser uses to deconstruct each sentence in the documents. Table 1 shows the various parts of speech (or syntactic categories) covered by our grammar. These syntactic categories are based on well-established part-of-speech tagging guidelines for English [58].
{< >? < . * > * < . * > * < . * >? (< >? < >? < . * > * < . * > * )? } In the grammar above, the "?" and "*" characters represent "optional" and "zero or more occurrences" respectively. Our grammar is aimed at generating keyphrases that capture both context and sentiment of a conversation using nouns, adjectives, and verbs. Research has shown that nouns are most useful in knowing the context of a conversation (i.e., what is being discussed) [59], while verbs and adjectives are important for sentiment detection [60]. Determiners and prepositions are also captured by the grammar since they usually co-occur with noun or adjective phrases (e.g., a meal for six people, a hospital on the hilltop, etc.).

Sentence Breaking and Tokenization
Next, each document is split into sentences, and then each sentence is split into tokens or words. The sentence breaking task is achieved using an unsupervised algorithm that considers abbreviations, collocations, capitalizations, and punctuations to detect sentence boundaries [61].

Part-of-Speech (PoS) Tagging
The tagging module associates each token with its part of speech. The part of speech tags are based on the Penn Treebank tagset [58,62], some of which are shown in Table 1.

Lemmatization
Each token is reduced to its root form, depending on its part of speech. This activity is called lemmatization. For example, worse and better which are both adjectives will become bad and good respectively. Prior to lemmatization, each token is converted to lowercase. While [63] applied stemming for its tokens, we chose lemmatization over stemming since lemmatization returns root words that are always meaningful and exist in the English dictionary. Stemming, on the other hand, may return root words that have no meaning at all since it merely removes prefixes or suffixes based on rule-based method [64].

Syntactic Parsing
The syntactic parsing module deconstructs each sentence into a parse tree and then creates chunks or phrases based on the grammar or POS pattern defined in the first step. In other words, the parser's chunking process involves matching phrases composed of an optional determiner, zero or more of any time of adjective, zero or more of any type of noun, any type of verb (but optional), as well as an optional component. This component consists of an optional preposition, an optional determiner, zero or more of any type of adjective, and zero or more of any type of noun. The output of this stage is the candidate themes ( ℎ ).

Transformation and Filtering
In this stage, themes that are stopwords (i.e., words that are commonly used, such as the, a, an, with, in, that, etc.) are removed from ℎ using a predefined list compiled from multiple sources such as [65]. Also, a subset of are removed from the start and end of (and from within) the remaining themes in ℎ such that the meaning of the themes is preserved. Afterwards, duplicates were removed from ℎ . In addition, themes containing more than ten words are removed from ℎ . While previous research excluded themes above length six [50], we excluded themes above length ten to prevent losing important themes that would have enriched insights from this paper. Since our focus is on opinionated themes (i.e., positive and negative themes), we applied a filtering technique that involves computing sentiment score for each theme and discarding non-opinionated themes.

Sentiment Scoring
To determine opinionated themes in ℎ , the scoring module computes sentiment score, , ranging from −1 to +1 for each theme using the VADER lexicon-based algorithm [66]. Afterwards, each theme is assigned a polarity based on the sentiment score using the criteria in [66] and shown in Table 2. Themes with the neutral polarity are excluded from ℎ since they are not opinionated.

Theme Categorization
Next, we recruited four reviewers to categorize related themes into a broader theme using thematic analysis method. We assigned the negative themes to a group of two reviewers (G1) and the positive themes to a second group of two reviewers (G2). Each reviewer independently examines the themes iteratively and continues to categorize related themes until saturation level is reached (i.e., no new categories were emerging from the themes). We measured interrater reliability using the percentage agreement metric [67]. The percentage interrater reliability score for G1 is 98.0% while the score for G2 is 99.3%.

Results
In this section, we discuss the results of our experiments and theme categorization. From the large corpus used for the experiment, a total of 427,875 unique negative themes and 520,685 unique positive themes were automatically generated. Figure 3 shows top 130 sample negative themes and their dominance in terms of frequency of occurrence. Our results revealed that death (n=10,187) is the dominant theme, followed by die (n=7,240), fight (n=5,891), bad (n=3,808), kill (n=3,668), lose (n=3,631), pay (n=3486), leave (n=3,234), crisis (n=2,783), hard (n=2,720), worry (n=2,476), sick (n=2,314), sad (n=2,129), and so on. Figure 4    . Our results revealed that help (n=18,498) is the dominant theme, followed by hope (n=7,708), protect (n=7,130), love (n=6,895), support (n=6,198), good (n=5,740), share (n=5,187), care (n=4,917), stay safe (n=4,917), and so on. Figure 6 shows more positive themes, such as keep everyone safe, clean environment, trust scientific data, create cure, economic relief, encourage business, remain strong, good mask, social distancing best way, generous, respect human right, help prevent further spread, pray for health, social solidarity, support relief effort, protect health worker, good immune system, practice good hand hygiene, speak truth, expand testing, protect vulnerable people, free treatment, ease anxiety, etc.  Table 3). Figure 7 shows the 15 negative theme categories and the corresponding number of themes under each category, while Figure 8 shows the negative theme categories and the total number of comments for each category. Frustration due to life disruptions emerged as the top negative theme category with the highest number of comments, followed by Increased mortality, Comparison with other diseases or incidents, Nature of the disease, and Harassment. On the other hand, Table 4 shows the 20 positive theme categories, description, and sample comments. Figure 9 shows the corresponding number of themes under each positive theme category, while Figure 10 shows the total number of comments for each theme category. Public awareness emerged as the top positive theme category based on the number of comments, followed by Spiritual support, Encouragement, and Charity.

Negative Themes
We refer to the theme categories as simply "themes" and the various themes under each category as "subthemes" in the remaining part of this paper.

Principal Results
In this paper, we analyzed social media comments to uncover insights regarding people's opinions and perceptions toward the COVID-19 pandemic using contextaware NLP approach. Our empirical findings revealed negative and positive themes (see Tables 3 and 4) representing negative and positive impact of COVID-19 pandemic and coping mechanisms on the world population. We discussed the implications of the negative themes in this section and then recommend interventions that can help tackle these issues based on the positive themes and other remedial ideas rooted in research. Health-related issues Evidence shows a rapid increase in the number of COVID-19 cases and a high casefatality rate of 7.2% [68]. In addition, substantial number of infected patients had severe pneumonia or were critically ill [68]. Another evidence revealed the mental health issues experienced by people and health professionals directly impacted by COVID-19 pandemic [69], as well as the global healthcare systems' inability to deal with the outbreak [70]. The themes under this category are discussed in the following subsections. They align with existing research and uncovered additional insights with respect to the health-related issues caused by COVID-19 and witnessed by people globally.

Health concerns
Based on our findings, people experienced various mental health issues (such as anxiety, depression, stress, obsessive compulsive disorder, etc.) during the pandemic. This is possibly due to the length of time spent staying at home (which may be traumatic for some people while causing loneliness for others), worrying about being infected with the disease and difficult living conditions, as well as guilt on the part of healthcare workers who feel responsible for being unable to save their patients from death. Research confirms that worry is associated with anxiety and depression [71]. Cases of mental health disorders linked to COVID-19 have also been reported [72]. "100 more UK deaths in last 24h alone. These are not all elderly co-morbid people. Among these are the young, and the fit..." [C940] Struggling health systems Health systems around the world are struggling to cope with the surge in the number of COVID-19 patients, and in most cases are unable to admit patients due to limited resources [73]. Research has shown that healthcare burden due to COVID-19 is associated with the increase in mortality rate [74]. As revealed in the sample comments below, our findings corroborated evidence of overstretched global health systems during this pandemic. Fitness issues Evidence argues the prevalence of physical inactivity globally due to nationwide quarantine or lockdown [75]. This is confirmed in our findings which show that people have trouble staying fit due to inability to control eating habits or urges while at home, as well as personal dislike for indoor-only workouts, as shown in the comments below. Physical inactivity has been linked to coronary heart disease, diabetes, stroke, and mental health issues [76][77][78] which, in turn, are risk factors for mortality in COVID-19 adult inpatients [79].
"…severely missing my gym, missing routine, and cannot control my eating while at home. Things are getting bad." [C9002] "During this shelter in place, I was gonna eat healthy and kill some workouts.

But instead I've been Guy Fieri'ing around the kitchen sampling all my quarantine food every 2 hours.
At this point, which will get me firstcoronavirus or a coronary?"

Nature of disease
People expressed their opinion about the nature of COVID-19 based on their experiences and information available to them. As shown in the sample comments below, people with underlying health conditions (e.g., diabetes, heart disease) are at higher risk of developing severe complications from the disease. In addition, the asymptotic attribute of COVID-19 is also discussed, and the possibility of the virus to infect some critical immune cells that may lead to the failure of sensitive organs like the lungs. People also perceived the disease as racial-or nationality-independent but seems to pose more risk to men than women. The disease is also seen as highly contagious and shows symptoms such as cough, fever, fatigue, loss of smell, muscle aches, and respiratory-related symptoms (e.g., shortness of breath). These findings align with clinical evidence regarding COVID-19 [80][81][82][83][84][85]. "Coronavirus is a disease that pays no attention to borders, race or nationality.
However, it appears COVID-19 does pose a noticeably bigger threat to men than it does to women." [C1902] "This is absolutely true. If you have a combination of cough, fever, problems smelling, weakness, muscle aches or shortness of breath, assume you have covid19. Don't bother getting tested. I know of many docs who don't test anymore if patient has obvious symptoms." [C2729] Rising number of cases Our findings show that more people are getting infected with COVID-19 in many parts of the world, as shown in the sample comments below. Evidence confirms increasing number of COVID-19 cases in North America [86,87], Europe [88], as well as a growing concern for vulnerable continents such as Africa [89].
"There is rapid increase in cases of COVID19 in India...I request PM to extend the lockdown to avoid community spread." [C1325] "Despite infection cases increasing at exponential rate doubling every 3 days, Trump pushes workers to risk their lives for economy..." [C6522]

Comparison with other diseases or incidents
Our findings reveal that people compare COVID-19 with other diseases such as flu (e.g., Spanish flu and H1N1 swine flu) and SARS, as well as with more extreme incidents such as war. However, while some people tend to downplay the severity of COVID-19 (see [C647]), others think it is dangerous or frightening (see [C922] and [C45]). Research shows that COVID-19 has a higher transmissibility rate than SARS [90] and killed more people than SARS and MERS combined [91], thereby making it a highly contagious and lethal disease.
"It is just another strain of flu. People with weak and have health problem it will affect different than people with stronger and not so much health problems. "This is a war. We need to protect ourselves and minimize unnecessary contact to avoid another Spanish flu that killed 50 million people..." [C45]

Psychosocial issues
Expression of Fear and Panic shopping Based on our findings, people are fearful or scared about COVID-19 and while many expressed genuine fear (including those who had lost loved ones to the disease, contracted the disease, or had an infected family member), others attributed it to fear mongering that is further amplified by the media. As a result of this fear, many people engage in panic buying to stockpile essential items so they can stay indoors/limit movements for some days or weeks to keep themselves and their families safe. Below are sample comments: "Very frightening when people who have travelled think that covid cannot affect them. Such foolish behaviour and thoughts putting all of us at risk. Those who travelled please STOP moving around and be at home." [C8887] "Fear mongering through projecting number of possible deaths. The media is disgusting." [C5559] "Everyone who is panic shopping is driving my family and me nuts...Everyone in our area is panic-buying groceries. We can't get noodles, rice, or really any real staple foods. We hardly have any food already. I'm kinda scared." [C2937] Work-from-home complaints Furthermore, the pandemic triggered work-from-home (or remote work) measure to promote continuity of businesses during lockdown [92], but this may have negative implications on people's lifestyle and wellbeing. For example, people found consistently working from home exhausting, boring, and distracting with kids at home. In addition, people living in countries without stable electricity and strong internet found it difficult and more costly to work from home, as they have to fuel their generators and pay more for considerably good internet connectivity. Evidence shows that people work longer hours at home than onsite due to difficulty in maintaining clear delineation between work and non-work domains [93], thereby leading to work-family conflict and strain [94]. Below are sample comments:  Figure 8). Based on our findings, this frustration is mostly due to decreased leisure and interaction with friends/family, authorities' actions/inactions, as well as uncertainty of upcoming situation which leads to cognitive dissonance [95], insecurity, and mental discomfort [96]. People expressed their frustrations using words reflecting anger and unhappiness/sadness, as shown in the sample comments below. Research shows that positive emotions (e.g., happiness) and life satisfaction decreased during COVID-19 pandemic [97]. Therefore, it is unsurprising that people missed (and crave for) their pre-pandemic lives, in retrospection (see [C377]

Recommended interventions for addressing the negative issues
As lockdown and physical distancing persists, people with health concerns should be able to receive medical attention without visiting a hospital. Considering the proliferation of smartphones and the current wave of global digitization, digital interventions using mobile, artificial intelligence (AI), internet of things (IoT), and virtual reality technologies have been shown to be effective for delivering remote healthcare (or telehealth) to patients [112][113][114][115][116][117]. This is based on our findings under the innovative research positive theme (see Table 4) which revealed global research efforts to create digital interventions using emerging technologies to address the health crisis caused by COVID-19. For example, mobile apps that detect mental health issues (e.g., depression and anxiety) based on phone sensors (or wearable sensors) data and self-reports using machine learning/deep learning models, and then guide users through therapeutic procedures or treatments will be useful tools during and after the pandemic. In addition, these apps should allow users to book appointment with doctors/clinicians/therapists and access remote medical advice, diagnosis, and treatments when necessary.
Also, data-driven surveillance systems based on artificial intelligence that predict location of next COVID-19 outbreak can enhance the effectiveness of containment efforts, thereby slowing the spread of the disease and reducing case-fatality rate. Furthermore, the development of curative solutions or treatments (see Table 4), can be accelerated by leveraging machine learning/deep learning algorithms. For example, deep learning models can be used to predict chemical compounds that can halt viral replication, as well as to suggest drugs that can be effective against the virus.
To address fitness issues during lockdown, physical activity (which is one of the positive themes in our results) programs or sessions with personalized feedback delivered through mobile apps will be helpful. Research has shown that smartphone-based health programs yield significant weight loss and increase physical activity [118]. There is also an urgent need to strengthen the global healthcare systems to cope with current and future pandemics through public and private investments in the health sector on an ongoing basis, such as provision of public health infrastructure that is robust and adequate for the target population and easily accessible, as well as the provision of health insurance for everyone irrespective of financial status.
Public awareness (which emerged as the top positive theme in our findings) is also crucial for addressing negative issues arising from COVID-19 by providing timely and accurate information to people, which can be lifesaving. To reach wider audience in an efficient manner and with less cost, public awareness can be delivered through mobile technologies such as mobile-driven and voice-enabled conversational AI agents (or chatbots) with access to evidence-based and clinically validated resources (e.g., precautionary or safety measures approved by public health agencies and organizations, as well as government-approved policies or guidelines) can deliver accurate information regarding COVID-19 to people in their own native language (and in an interactive fashion) through their smartphones. These chatbots can also be made to route difficult questions to health experts for real-time feedback within the same chat session. This will help to improve people's understanding of the disease, including how it differs from other infectious diseases, and how to protect themselves and their families from getting infected with COVID-19. In addition, people will be empowered with information required to effectively respond to fear mongering, domestic violence, and harassment. Evidence already shows the deployment of multilingual chatbot for public health awareness on coronavirus symptoms, diagnosis, and precautionary measures [119]. Furthermore, chatbots can also respond to emergencies by contacting appropriate security agencies and emergency response teams on behalf of the users. Moreover, chatbots can deliver evidence-based therapeutic interventions to people, while coordinating with specialists behind the scenes where necessary.
For people with non-smartphone devices, public health agencies can partner with telecommunication companies to deliver COVID-19-related information directly to their phones as text messages at regular intervals using the short messaging service (SMS). Social media is another platform through which evidence-based information can be shared with the public but may be overshadowed by fake news or false information which is mostly shared on social media [120]. Nevertheless, official COVID-19-related channels managed by (or in conjunction with) reputable international health organizations (e.g., World Health Organization) or local health authorities within the social media platforms, many of which have already been deployed, provide accurate information/updates about COVID-19 cases, fatality rates, and safety measures/guidelines [121,122]. In addition, people receive location-based updates on these channels, including emergency alerts, in a timely and effective manner.
Finally, based on our findings (see Table 4), connectedness with family and friends, encouragement, spiritual support, and charity can help to ease people's frustrations, anxiety, and trauma (due to life disruptions caused by the pandemic) by addressing their emotional, physical, and spiritual needs. Evidence shows that psychological first aid and spiritual care can promote a sense of safety, calmness, self-and collective-efficacy, connectedness, and hope, as well as help people confront and overcome fear [123]. Therefore, people should endeavour to frequently communicate and follow up with loved ones (through direct voice/video calls or using social media), encourage others in distress to stay calm and remain positive, identify people's immediate needs and offer necessary assistance, help people find hope and meaning, and ensure safety and comfort of vulnerable population.
Mobile technology can play a key role in facilitating easy access to relief packages. For instance, mobile apps can be deployed with geolocation and multilingual features to help people locate the nearest food bank and charity organizations offering assistance in their geographical area. In addition, charity organizations can effectively mobilize and deliver relief items to more people, including individuals that are indisposed, based on data collected through these apps. Also, the elderly, the sick, and those in self-isolation can indicate their condition while requesting for relief so that their items can be delivered to their doorstep instead of picking it up. These apps can further integrate with other local and international charity organizations to widen the coverage of relief efforts. Recruitment of volunteers can also take place through these apps. The usage data collected can be further analyzed in real-time and used to predict the communities that are in dire need of assistance using machine learning or deep learning techniques.

Conclusions
In this paper, we explored the impact of the COVID-19 pandemic on people globally using social media data. We analyzed over 1 million comments obtained from six social media platforms using a seven-stage context-aware Natural Language Processing (NLP) approach to extract candidate themes or keyphrases which we further categorized into broader themes using thematic analysis. Our results revealed 34 negative themes, out of which 15 are health-related issues, psychosocial issues, and social issues related to the COVID-19 pandemic from the public perspective. Top health-related issues include increased mortality, comparison with other diseases or incidents, nature of disease, and health concerns, while top psychosocial issues include frustrations due to life disruptions, panic shopping, and expression of fear. Top social issues include harassment and domestic violence.
Besides the negative themes, 20 positive themes emerged from our results. Some of the positive themes include public awareness, encouragement, gratitude, cleaner environment, online learning, charity, spiritual support, and innovative research. We reflected on our findings and recommend interventions that can help address the health, psychosocial, and social issues based on the positive themes and other remedial ideas rooted in research.
Digital interventions using emerging technologies such as mobile apps, artificial intelligence (AI), internet of things (IoT), and virtual reality will play a major role in delivering remote healthcare (i.e., telemedicine or telehealth) to people in the comfort of their homes, including empowering them to self-manage their health and wellness. This will help to curb the spread of COVID-19 and future infectious diseases since many people will stay away from hospitals (or clinics) to book appointments or see doctors (or other healthcare professionals) unless it is absolutely necessary to visit, thereby keeping health workers and patients safe. These technologies are also useful in providing timely and accurate information about COVID-19 symptoms, diagnosis, treatment, precautionary/safety measures and guidelines, and other relevant information to target audience worldwide. Finally, digital interventions and other interventions discussed in this paper can help address the emotional, physical, and spiritual needs of people who are traumatized or frustrated by the disruptions caused by the pandemic. They also inform governments, health professionals and agencies, and institutions on how to react to the current COVID-19 pandemic, as well as future pandemics.