Pediatric Cancer Communication on Twitter: Natural Language Processing and Qualitative Content Analysis

BACKGROUND

During the COVID-19 pandemic, Twitter (recently rebranded as "X") was the most widely used social media platform with over 2 million cancer-related tweets. The increasing use of social media among patients and family members, providers, and organizations has allowed for novel methods of studying cancer communication.

OBJECTIVE

This study aimed to examine pediatric cancer-related tweets to capture the experiences of patients and survivors of cancer, their caregivers, medical providers, and other stakeholders. We assessed the public sentiment and content of tweets related to pediatric cancer over a time period representative of the COVID-19 pandemic.

METHODS

All English-language tweets related to pediatric cancer posted from December 11, 2019, to May 7, 2022, globally, were obtained using the Twitter application programming interface. Sentiment analyses were computed based on Bing, AFINN, and NRC lexicons. We conducted a supplemental nonlexicon-based sentiment analysis with ChatGPT (version 3.0) to validate our findings with a random subset of 150 tweets. We conducted a qualitative content analysis to manually code the content of a random subset of 800 tweets.

RESULTS

A total of 161,135 unique tweets related to pediatric cancer were identified. Sentiment analyses showed that there were more positive words than negative words. Via the Bing lexicon, the most common positive words were support, love, amazing, heaven, and happy, and the most common negative words were grief, risk, hard, abuse, and miss. Via the NRC lexicon, most tweets were categorized under sentiment types of positive, trust, and joy. Overall positive sentiment was consistent across lexicons and confirmed with supplemental ChatGPT (version 3.0) analysis. Percent agreement between raters for qualitative coding was 91%, and the top 10 codes were awareness, personal experiences, research, caregiver experiences, patient experiences, policy and the law, treatment, end of life, pharmaceuticals and drugs, and survivorship. Qualitative content analysis showed that Twitter users commonly used the social media platform to promote public awareness of pediatric cancer and to share personal experiences with pediatric cancer from the perspective of patients or survivors and their caregivers. Twitter was frequently used for health knowledge dissemination of research findings and federal policies that support treatment and affordable medical care.

CONCLUSIONS

Twitter may serve as an effective means for researchers to examine pediatric cancer communication and public sentiment around the globe. Despite the public mental health crisis during the COVID-19 pandemic, overall sentiments of pediatric cancer-related tweets were positive. Content of pediatric cancer tweets focused on health and treatment information, social support, and raising awareness of pediatric cancer.

A Content Analysis of Indoor Tanning Twitter Chatter During COVID-19 Shutdowns: Cross-Sectional Qualitative Study

BACKGROUND

Indoor tanning is a preventable risk factor for skin cancer. Statewide shutdowns during the COVID-19 pandemic resulted in temporary closures of tanning businesses. Little is known about how tanners reacted to losing access to tanning businesses.

OBJECTIVE

This study aimed to analyze Twitter (subsequently rebranded as X) chatter about indoor tanning during the statewide pandemic shutdowns.

METHODS

We collected tweets from March 15 to April 30, 2020, and performed a directed content analysis of a random sample of 20% (1165/5811) of tweets from each week. The 2 coders independently rated themes (κ=0.67-1.0; 94%-100% agreement).

RESULTS

About half (589/1165, 50.6%) of tweets were by people unlikely to indoor tan, and most of these mocked tanners or the act of tanning (562/589, 94.9%). A total of 34% (402/1165) of tweets were posted by users likely to indoor tan, and most of these (260/402, 64.7%) mentioned missing tanning beds, often citing appearance- or mood-related reasons or withdrawal. Some tweets by tanners expressed a desire to purchase or use home tanning beds (90/402, 22%), while only 3.9% (16/402) mentioned tanning alternatives (eg, self-tanner). Very few tweets (29/1165, 2.5%) were public health messages about the dangers of indoor tanning.

CONCLUSIONS

Findings revealed that during statewide shutdowns, half of the tweets about indoor tanning were mocking tanning bed users and the tanned look, while about one-third were indoor tanners reacting to their inability to access tanning beds. Future work is needed to understand emerging trends in tanning post pandemic.

Content and sentiment analysis of gabapentinoid-related tweets: An infodemiology study

INTRODUCTION

The increasing number of gabapentinoid (pregabalin and gabapentin) harms, including deaths observed across countries is concerning to health-care professionals and policy makers. However, it is unclear if the public shares these concerns. This study aimed to describe posts related to gabapentinoids, conduct a content analysis to identify common themes and describe adverse events or symptoms.

METHODS

Keywords of 'pregabalin' or 'Lyrica' or 'gabapentin' or 'Neurontin' were used to search for related tweets posted by people in the community between 8 March and 7 May 2021. Eligible tweets included a keyword in the post. We extracted de-identified data which included descriptive data of the total number of posts over time; and data on individual tweets including date, number of re-tweets and post content. Data were exported separately for pregabalin- and gabapentin-related tweets. A 20% random sample was used for the thematic analysis.

RESULTS

There were 2931 pregabalin-related tweets and 2736 gabapentin-related tweets. Thematic analysis revealed three themes (sharing positive experiences and benefits of taking gabapentinoids, people voicing their negative experiences, and people seeking opinions and sharing information). Positive experiences of gabapentinoids were related to sharing stories and giving advice. This was contrasted to negative experiences including ineffectiveness, withdrawals, side effects and frustration related to cost and insurance coverage. Brain fog was the most common adverse symptom reported. Gabapentinoid-related deaths were only mentioned in three tweets.

DISCUSSION

The increasing public health concern of gabapentinoid-related deaths was not translated to Twitter discussions.

Use of Social Media for Health Advocacy for Digital Communities: Descriptive Study

BACKGROUND

There has been a growth surge in the use of social media among individuals today. The widespread adoption of these platforms, coupled with their engaging features, presents a unique opportunity for the dissemination of health advocacy information. Social media is known as a powerful tool used to share health policy and advocacy efforts and disseminate health information to digital community members and networks. Yet, there is still a gap in the full exploitation of this powerful instrument, among health care professionals, for health advocacy campaigns.

OBJECTIVE

This paper aims to describe the process of mobilizing social media platforms such as Twitter (rebranded to X Corp in 2023) for health advocacy of the digital community. Additionally, it aims to share the lessons and insights gained during this digital health advocacy engagement process.

METHODS

We performed a comprehensive review of Twitter analytical data to examine the impact of our social media posts. We then consolidated these analytic reports with our meeting logs to describe our systematic, iterative, and collaborative design process to implement social media efforts and generate key lessons learned.

RESULTS

Our review of monthly Twitter analytical reports and regular team meeting logs revealed several themes for successful and less successful practices in relation to our social media-based health advocacy efforts. The successful practices noted by the team included using personable, picture-based tweets; using a series of posts on a particular topic rather than an isolated post; leveraging team members' and partners' collaborations in shared posts; incorporating hashtags in tweets; using a balanced mix of texts and graphics in posts; using inclusive (nondestigmatizing) languages in tweeted posts; and use of polls to share tweets. Among the many lessons learned, we also experienced limitations including a lack of comprehensive statistics on Twitter usage for health care-related purposes such as health advocacy and limits in collating the estimates of the actual impact made on the intended digital community members by our posts.

CONCLUSIONS

Twitter has been successfully used in promoting health advocacy content, and the social media team aims to explore other social media platforms that have a wider reach than Twitter. We will continue making necessary adjustments in strategies, techniques, and styles to engage the audience as we expand onto new platforms like Instagram and TikTok for health advocacy promotions.

Assessment of the Early Detection of Anosmia and Ageusia Symptoms in COVID-19 on Twitter: Retrospective Study

BACKGROUND

During the unprecedented COVID-19 pandemic, social media has been extensively used to amplify the spread of information and to express personal health-related experiences regarding symptoms, including anosmia and ageusia, 2 symptoms that have been reported later than other symptoms.

OBJECTIVE

Our objective is to investigate to what extent Twitter users reported anosmia and ageusia symptoms in their tweets and if they connected them to COVID-19, to evaluate whether these symptoms could have been identified as COVID-19 symptoms earlier using Twitter rather than the official notice.

METHODS

We collected French tweets posted between January 1, 2020, and March 31, 2020, containing anosmia- or ageusia-related keywords. Symptoms were detected using fuzzy matching. The analysis consisted of 3 parts. First, we compared the coverage of anosmia and ageusia symptoms in Twitter and in traditional media to determine if the association between COVID-19 and anosmia or ageusia could have been identified earlier through Twitter. Second, we conducted a manual analysis of anosmia- and ageusia-related tweets to obtain quantitative and qualitative insights regarding their nature and to assess when the first associations between COVID-19 and these symptoms were established. We randomly annotated tweets from 2 periods: the early stage and the rapid spread stage of the epidemic. For each tweet, each symptom was annotated regarding 3 modalities: symptom (yes or no), associated with COVID-19 (yes, no, or unknown), and whether it was experienced by someone (yes, no, or unknown). Third, to evaluate if there was a global increase of tweets mentioning anosmia or ageusia in early 2020, corresponding to the beginning of the COVID-19 epidemic, we compared the tweets reporting experienced anosmia or ageusia between the first periods of 2019 and 2020.

RESULTS

In total, 832 (respectively 12,544) tweets containing anosmia (respectively ageusia) related keywords were extracted over the analysis period in 2020. The comparison to traditional media showed a strong correlation without any lag, which suggests an important reactivity of Twitter but no earlier detection on Twitter. The annotation of tweets from 2020 showed that tweets correlating anosmia or ageusia with COVID-19 could be found a few days before the official announcement. However, no association could be found during the first stage of the pandemic. Information about the temporality of symptoms and the psychological impact of these symptoms could be found in the tweets. The comparison between early 2020 and early 2019 showed no difference regarding the volumes of tweets.

CONCLUSIONS

Based on our analysis of French tweets, associations between COVID-19 and anosmia or ageusia by web users could have been found on Twitter just a few days before the official announcement but not during the early stage of the pandemic. Patients share qualitative information on Twitter regarding anosmia or ageusia symptoms that could be of interest for future analyses.

Examining Public Awareness of Ageist Terms on Twitter: Content Analysis

Background

The World Health Organization, the Centers for Disease Control and Prevention, and the Gerontological Society of America have made efforts to raise awareness on ageist language and propose appropriate terms to denote the older adult population. The COVID-19 pandemic and older adults' vulnerability to the disease have perpetuated hostile ageist discourse on social media. This is an opportune time to understand the prevalence and use of ageist language and discuss the ways forward.

Objective

This study aimed to understand the prevalence and situated use of ageist terms on Twitter.

Methods

We collected 60.32 million tweets between March and July 2020 containing terms related to COVID-19. We then conducted a mixed methods study comprising a content analysis and a descriptive quantitative analysis.

Results

A total of 58,930 tweets contained the ageist terms "old people" or "elderly." The more appropriate term "older adult" was found in 11,328 tweets. Twitter users used ageist terms (eg, "old people" and "elderly") to criticize ageist messages (17/60, 28%), showing a lack of understanding of appropriate terms to describe older adults. Highly hostile ageist content against older adults came from tweets that contained the derogatory terms "old people" (22/30, 73%) or "elderly" (13/30, 43%).

Conclusions

The public discourse observed on Twitter shows a continued lack of understanding of appropriate terms to use when referring to older adults. Effort is needed to eliminate the perpetuation of ageist messages that challenge healthy aging. Our study highlights the need to inform the public about appropriate language use and ageism.

Evaluating the Global Digital Impact of Psoriasis Action Month and World Psoriasis Day: Serial Cross-Sectional Study

Collapse

Twitter Sentiment About the US Federal Tobacco 21 Law: Mixed Methods Analysis

BACKGROUND

On December 20, 2019, the US "Tobacco 21" law raised the minimum legal sales age of tobacco products to 21 years. Initial research suggests that misinformation about Tobacco 21 circulated via news sources on Twitter and that sentiment about the law was associated with particular types of tobacco products and included discussions about other age-related behaviors. However, underlying themes about this sentiment as well as temporal trends leading up to enactment of the law have not been explored.

OBJECTIVE

This study sought to examine (1) sentiment (pro-, anti-, and neutral policy) about Tobacco 21 on Twitter and (2) volume patterns (number of tweets) of Twitter discussions leading up to the enactment of the federal law.

METHODS

We collected tweets related to Tobacco 21 posted between September 4, 2019, and December 31, 2019. A 2% subsample of tweets (4628/231,447) was annotated by 2 experienced, trained coders for policy-related information and sentiment. To do this, a codebook was developed using an inductive procedure that outlined the operational definitions and examples for the human coders to annotate sentiment (pro-, anti-, and neutral policy). Following the annotation of the data, the researchers used a thematic analysis to determine emergent themes per sentiment category. The data were then annotated again to capture frequencies of emergent themes. Concurrently, we examined trends in the volume of Tobacco 21-related tweets (weekly rhythms and total number of tweets over the time data were collected) and analyzed the qualitative discussions occurring at those peak times.

RESULTS

The most prevalent category of tweets related to Tobacco 21 was neutral policy (514/1113, 46.2%), followed by antipolicy (432/1113, 38.8%); 167 of 1113 (15%) were propolicy or supportive of the law. Key themes identified among neutral tweets were news reports and discussion of political figures, parties, or government involvement in general. Most discussions were generated from news sources and surfaced in the final days before enactment. Tweets opposing Tobacco 21 mentioned that the law was unfair to young audiences who were addicted to nicotine and were skeptical of the law's efficacy and importance. Methods used to evade the law were found to be represented in both neutral and antipolicy tweets. Propolicy tweets focused on the protection of youth and described the law as a sensible regulatory approach rather than a complete ban of all products or flavored products. Four spikes in daily volume were noted, 2 of which corresponded with political speeches and 2 with the preparation and passage of the legislation.

CONCLUSIONS

Understanding themes of public sentiment-as well as when Twitter activity is most active-will help public health professionals to optimize health promotion activities to increase community readiness and respond to enforcement needs including education for retailers and the general public.

Perspectives and Experiences of Patients With Thyroid Cancer at a Global Level: Retrospective Descriptive Study of Twitter Data

BACKGROUND

Twitter has become a popular platform for individuals to broadcast their daily experiences and opinions on a wide range of topics and emotions. Tweets from patients with cancer could offer insights into their needs. However, limited research has been conducted using Twitter data to understand the needs of patients with cancer despite the substantial amount of health-related data posted on the platform daily.

OBJECTIVE

This study aimed to uncover the potential of using Twitter data to understand the perspectives and experiences of patients with thyroid cancer at a global level.

METHODS

 This retrospective descriptive study collected tweets relevant to thyroid cancer in 2020 using the Twitter scraping tool. Only English-language tweets were included, and data preprocessing was performed to remove irrelevant tweets, duplicates, and retweets. Both tweets and Twitter users were manually classified into various groups based on the content. Each tweet underwent sentiment analysis and was classified as either positive, neutral, or negative.

RESULTS

A total of 13,135 tweets related to thyroid cancer were analyzed. The authors of the tweets included patients with thyroid cancer (3225 tweets, 24.6%), patient's families and friends (2449 tweets, 18.6%), medical journals and media (1733 tweets, 13.2%), health care professionals (1093 tweets, 8.3%), and medical health organizations (940 tweets, 7.2%), respectively. The most discussed topics related to living with cancer (3650 tweets, 27.8%), treatment (2891 tweets, 22%), diagnosis (1613 tweets, 12.3%), risk factors and prevention (1137 tweets, 8.7%), and research (953 tweets, 7.3%). An average of 36 tweets pertaining to thyroid cancer were posted daily. Notably, the release of a film addressing thyroid cancer and the public disclosure of a news reporter's personal diagnosis of thyroid cancer resulted in a significant escalation in the volume of tweets. From the sentiment analysis, 53.5% (7025/13,135) of tweets were classified as neutral statements and 32.7% (4299/13,135) of tweets expressed negative emotions. Tweets from patients with thyroid cancer had the highest proportion of negative emotion (1385/3225 tweets, 42.9%), particularly when discussing symptoms.

CONCLUSIONS

 This study provides new insights on using Twitter data as a valuable data source to understand the experiences of patients with thyroid cancer. Twitter may provide an opportunity to improve patient and physician engagement or apply as a potential research data source.

Results and Methodological Implications of the Digital Epidemiology of Prescription Drug References Among Twitter Users: Latent Dirichlet Allocation (LDA) Analyses

BACKGROUND

Social media is an important information source for a growing subset of the population and can likely be leveraged to provide insight into the evolving drug overdose epidemic. Twitter can provide valuable insight into trends, colloquial information available to potential users, and how networks and interactivity might influence what people are exposed to and how they engage in communication around drug use.

OBJECTIVE

This exploratory study was designed to investigate the ways in which unsupervised machine learning analyses using natural language processing could identify coherent themes for tweets containing substance names.

METHODS

This study involved harnessing data from Twitter, including large-scale collection of brand name (N=262,607) and street name (N=204,068) prescription drug-related tweets and use of unsupervised machine learning analyses (ie, natural language processing) of collected data with data visualization to identify pertinent tweet themes. Latent Dirichlet allocation (LDA) with coherence score calculations was performed to compare brand (eg, OxyContin) and street (eg, oxys) name tweets.

RESULTS

We found people discussed drug use differently depending on whether a brand name or street name was used. Brand name categories often contained political talking points (eg, border, crime, and political handling of ongoing drug mitigation strategies). In contrast, categories containing street names occasionally referenced drug misuse, though multiple social uses for a term (eg, Sonata) muddled topic clarity.

CONCLUSIONS

Content in the brand name corpus reflected discussion about the drug itself and less often reflected personal use. However, content in the street name corpus was notably more diverse and resisted simple LDA categorization. We speculate this may reflect effective use of slang terminology to clandestinely discuss drug-related activity. If so, straightforward analyses of digital drug-related communication may be more difficult than previously assumed. This work has the potential to be used for surveillance and detection of harmful drug use information. It also might be used for appropriate education and dissemination of information to persons engaged in drug use content on Twitter.

Investigating the Role of Nutrition in Enhancing Immunity During the COVID-19 Pandemic: Twitter Text-Mining Analysis

BACKGROUND

The COVID-19 pandemic has brought to the spotlight the critical role played by a balanced and healthy diet in bolstering the human immune system. There is burgeoning interest in nutrition-related information on social media platforms like Twitter. There is a critical need to assess and understand public opinion, attitudes, and sentiments toward nutrition-related information shared on Twitter.

OBJECTIVE

This study uses text mining to analyze nutrition-related messages on Twitter to identify and analyze how the general public perceives various food groups and diets for improving immunity to the SARS-CoV-2 virus.

METHODS

We gathered 71,178 nutrition-related tweets that were posted between January 01, 2020, and September 30, 2020. The Correlated Explanation text mining algorithm was used to identify frequently discussed topics that users mentioned as contributing to immunity building against SARS-CoV-2. We assessed the relative importance of these topics and performed a sentiment analysis. We also qualitatively examined the tweets to gain a closer understanding of nutrition-related topics and food groups.

RESULTS

Text-mining yielded 10 topics that users discussed frequently on Twitter, viz proteins, whole grains, fruits, vegetables, dairy-related, spices and herbs, fluids, supplements, avoidable foods, and specialty diets. Supplements were the most frequently discussed topic (23,913/71,178, 33.6%) with a higher proportion (20,935/23,913, 87.75%) exhibiting a positive sentiment with a score of 0.41. Consuming fluids (17,685/71,178, 24.85%) and fruits (14,807/71,178, 20.80%) were the second and third most frequent topics with favorable, positive sentiments. Spices and herbs (8719/71,178, 12.25%) and avoidable foods (8619/71,178, 12.11%) were also frequently discussed. Negative sentiments were observed for a higher proportion of avoidable foods (7627/8619, 84.31%) with a sentiment score of -0.39.

CONCLUSIONS

This study identified 10 important food groups and associated sentiments that users discussed as a means to improve immunity. Our findings can help dieticians and nutritionists to frame appropriate interventions and diet programs.

Cervical Myelopathy and Social Media: Mixed Methods Analysis

BACKGROUND

Degenerative cervical myelopathy (DCM) is a progressive neurologic condition caused by age-related degeneration of the cervical spine. Social media has become a crucial part of many patients' lives; however, little is known about social media use pertaining to DCM.

OBJECTIVE

This manuscript describes the landscape of social media use and DCM in patients, caretakers, clinicians, and researchers.

METHODS

A comprehensive search of the entire Twitter application programing interface database from inception to March 2022 was performed to identify all tweets about cervical myelopathy. Data on Twitter users included geographic location, number of followers, and number of tweets. The number of tweet likes, retweets, quotes, and total engagement were collected. Tweets were also categorized based on their underlying themes. Mentions pertaining to past or upcoming surgical procedures were recorded. A natural language processing algorithm was used to assign a polarity score, subjectivity score, and analysis label to each tweet for sentiment analysis.

RESULTS

Overall, 1859 unique tweets from 1769 accounts met the inclusion criteria. The highest frequency of tweets was seen in 2018 and 2019, and tweets decreased significantly in 2020 and 2021. Most (888/1769, 50.2%) of the tweets' authors were from the United States, United Kingdom, or Canada. Account categorization showed that 668 of 1769 (37.8%) users discussing DCM on Twitter were medical doctors or researchers, 415 of 1769 (23.5%) were patients or caregivers, and 201 of 1769 (11.4%) were news media outlets. The 1859 tweets most often discussed research (n=761, 40.9%), followed by spreading awareness or informing the public on DCM (n=559, 30.1%). Tweets describing personal patient perspectives on living with DCM were seen in 296 (15.9%) posts, with 65 (24%) of these discussing upcoming or past surgical experiences. Few tweets were related to advertising (n=31, 1.7%) or fundraising (n=7, 0.4%). A total of 930 (50%) tweets included a link, 260 (14%) included media (ie, photos or videos), and 595 (32%) included a hashtag. Overall, 847 of the 1859 tweets (45.6%) were classified as neutral, 717 (38.6%) as positive, and 295 (15.9%) as negative.

CONCLUSIONS

When categorized thematically, most tweets were related to research, followed by spreading awareness or informing the public on DCM. Almost 25% (65/296) of tweets describing patients' personal experiences with DCM discussed past or upcoming surgical interventions. Few posts pertained to advertising or fundraising. These data can help identify areas for improvement of public awareness online, particularly regarding education, support, and fundraising.

Characterizing Twitter Content About HIV Pre-exposure Prophylaxis (PrEP) for Women: Qualitative Content Analysis

BACKGROUND

HIV remains a persistent health problem in the United States, especially among women. Approved in 2012, HIV pre-exposure prophylaxis (PrEP) is a daily pill or bimonthly injection that can be taken by individuals at increased risk of contracting HIV to reduce their risk of new infection. Women who are at risk of HIV face numerous barriers to HIV services and information, underscoring the critical need for strategies to increase awareness of evidence-based HIV prevention methods, such as HIV PrEP, among women.

OBJECTIVE

We aimed to identify historical trends in the use of Twitter hashtags specific to women and HIV PrEP and explore content about women and PrEP shared through Twitter.

METHODS

This was a qualitative descriptive study using a purposive sample of tweets containing hashtags related to women and HIV PrEP from 2009 to 2022. Tweets were collected via Twitter's API. Each Twitter user profile, tweet, and related links were coded using content analysis, guided by the framework of the Health Belief Model (HBM) to generate results. We used a factor analysis to identify salient clusters of tweets.

RESULTS

A total of 1256 tweets from 396 unique users were relevant to our study focus of content about PrEP specifically for women (1256/2908, 43.2% of eligible tweets). We found that this sample of tweets was posted mostly by organizations. The 2 largest groups of individual users were activists and advocates (61/396, 15.4%) and personal users (54/396, 13.6%). Among individual users, most were female (100/166, 60%) and American (256/396, 64.6%). The earliest relevant tweet in our sample was posted in mid-2014 and the number of tweets significantly decreased after 2018. We found that 61% (496/820) of relevant tweets contained links to informational websites intended to provide guidance and resources or promote access to PrEP. Most tweets specifically targeted people of color, including through the use of imagery and symbolism. In addition to inclusive imagery, our factor analysis indicated that more than a third of tweets were intended to share information and promote PrEP to people of color. Less than half of tweets contained any HBM concepts, and only a few contained cues to action. Lastly, while our sample included only tweets relevant to women, we found that the tweets directed to lesbian, gay, bisexual, transgender, queer (LGBTQ) audiences received the highest levels of audience engagement.

CONCLUSIONS

These findings point to several areas for improvement in future social media campaigns directed at women about PrEP. First, future posts would benefit from including more theoretical constructs, such as self-efficacy and cues to action. Second, organizations posting on Twitter should continue to broaden their audience and followers to reach more people. Lastly, tweets should leverage the momentum and strategies used by the LGBTQ community to reach broader audiences and destigmatize PrEP use across all communities.

Did the public attribute the Flint Water Crisis to racism as it was happening? Text analysis of Twitter data to examine causal attributions to racism during a public health crisis

The Flint Water Crisis (FWC) was an avoidable public health disaster that has profoundly affected the city's residents, a majority of whom are Black. Although many scholars and journalists have called attention to the role of racism in the water crisis, little is known about the extent to which the public attributed the FWC to racism as it was unfolding. In this study, we used natural language processing to analyze nearly six million Flint-related tweets posted between April 1, 2014, and June 1, 2016. We found that key developments in the FWC corresponded to increases in the number and percentage of tweets that mentioned terms related to race and racism. Similar patterns were found for other topics hypothesized to be related to the water crisis, including water and politics. Using sentiment analysis, we found that tweets with a negative polarity score were more common in the subset of tweets that mentioned terms related to race and racism when compared to the full set of tweets. Next, we found that word pairs that included terms related to race and racism first appeared after the January 2016 state and federal emergency declarations and a corresponding increase in media coverage of the FWC. We conclude that many Twitter users connected the events of the water crisis to race and racism in real-time. Given growing evidence of negative health effects of second-hand exposure to racism, this may have implications for understanding minority health and health disparities in the US.

The Public Health Contribution of Sentiment Analysis of Monkeypox Tweets to Detect Polarities Using the CNN-LSTM Model

Monkeypox is a rare disease caused by the monkeypox virus. This disease was considered eradicated in 1980 and was believed to affect rodents and not humans. However, recent years have seen a massive outbreak of monkeypox in humans, setting off worldwide alerts from health agencies. As of September 2022, the number of confirmed cases in Peru had reached 1964. Although most monkeypox patients have been discharged, we cannot neglect the monitoring of the population with respect to the monkeypox virus. Lately, the population has started to express their feelings and opinions through social media, specifically Twitter, as it is the most used social medium and is an ideal space to gather what people think about the monkeypox virus. The information imparted through this medium can be in different formats, such as text, videos, images, audio, etc. The objective of this work is to analyze the positive, negative, and neutral feelings of people who publish their opinions on Twitter with the hashtag #Monkeypox. To find out what people think about this disease, a hybrid-based model architecture built on CNN and LSTM was used to determine the prediction accuracy. The prediction result obtained from the total monkeypox data was 83% accurate. Other performance metrics were also used to evaluate the model, such as specificity, recall level, and F1 score, representing 99%, 85%, and 88%, respectively. The results also showed the polarity of feelings through the CNN-LSTM confusion matrix, where 45.42% of people expressed neither positive nor negative opinions, while 19.45% expressed negative and fearful feelings about this infectious disease. The results of this work contribute to raising public awareness about the monkeypox virus.

A BERT Framework to Sentiment Analysis of Tweets

Sentiment analysis has been widely used in microblogging sites such as Twitter in recent decades, where millions of users express their opinions and thoughts because of its short and simple manner of expression. Several studies reveal the state of sentiment which does not express sentiment based on the user context because of different lengths and ambiguous emotional information. Hence, this study proposes text classification with the use of bidirectional encoder representations from transformers (BERT) for natural language processing with other variants. The experimental findings demonstrate that the combination of BERT with CNN, BERT with RNN, and BERT with BiLSTM performs well in terms of accuracy rate, precision rate, recall rate, and F1-score compared to when it was used with Word2vec and when it was used with no variant.

MonkeyPox2022Tweets: A Large-Scale Twitter Dataset on the 2022 Monkeypox Outbreak, Findings from Analysis of Tweets, and Open Research Questions

The mining of Tweets to develop datasets on recent issues, global challenges, pandemics, virus outbreaks, emerging technologies, and trending matters has been of significant interest to the scientific community in the recent past, as such datasets serve as a rich data resource for the investigation of different research questions. Furthermore, the virus outbreaks of the past, such as COVID-19, Ebola, Zika virus, and flu, just to name a few, were associated with various works related to the analysis of the multimodal components of Tweets to infer the different characteristics of conversations on Twitter related to these respective outbreaks. The ongoing outbreak of the monkeypox virus, declared a Global Public Health Emergency (GPHE) by the World Health Organization (WHO), has resulted in a surge of conversations about this outbreak on Twitter, which is resulting in the generation of tremendous amounts of Big Data. There has been no prior work in this field thus far that has focused on mining such conversations to develop a Twitter dataset. Furthermore, no prior work has focused on performing a comprehensive analysis of Tweets about this ongoing outbreak. To address these challenges, this work makes three scientific contributions to this field. First, it presents an open-access dataset of 556,427 Tweets about monkeypox that have been posted on Twitter since the first detected case of this outbreak. A comparative study is also presented that compares this dataset with 36 prior works in this field that focused on the development of Twitter datasets to further uphold the novelty, relevance, and usefulness of this dataset. Second, the paper reports the results of a comprehensive analysis of the Tweets of this dataset. This analysis presents several novel findings; for instance, out of all the 34 languages supported by Twitter, English has been the most used language to post Tweets about monkeypox, about 40,000 Tweets related to monkeypox were posted on the day WHO declared monkeypox as a GPHE, a total of 5470 distinct hashtags have been used on Twitter about this outbreak out of which #monkeypox is the most used hashtag, and Twitter for iPhone has been the leading source of Tweets about the outbreak. The sentiment analysis of the Tweets was also performed, and the results show that despite a lot of discussions, debate, opinions, information, and misinformation, on Twitter on various topics in this regard, such as monkeypox and the LGBTQI+ community, monkeypox and COVID-19, vaccines for monkeypox, etc., "neutral" sentiment was present in most of the Tweets. It was followed by "negative" and "positive" sentiments, respectively. Finally, to support research and development in this field, the paper presents a list of 50 open research questions related to the outbreak in the areas of Big Data, Data Mining, Natural Language Processing, and Machine Learning that may be investigated based on this dataset.

Public sentiments toward COVID-19 vaccines in South African cities: An analysis of Twitter posts

Amidst the COVID-19 vaccination, Twitter is one of the most popular platforms for discussions about the COVID-19 vaccination. These types of discussions most times lead to a compromise of public confidence toward the vaccine. The text-based data generated by these discussions are used by researchers to extract topics and perform sentiment analysis at the provincial, country, or continent level without considering the local communities. The aim of this study is to use clustered geo-tagged Twitter posts to inform city-level variations in sentiments toward COVID-19 vaccine-related topics in the three largest South African cities (Cape Town, Durban, and Johannesburg). VADER, an NLP pre-trained model was used to label the Twitter posts according to their sentiments with their associated intensity scores. The outputs were validated using NB (0.68), LR (0.75), SVMs (0.70), DT (0.62), and KNN (0.56) machine learning classification algorithms. The number of new COVID-19 cases significantly positively correlated with the number of Tweets in South Africa (Corr = 0.462, P < 0.001). Out of the 10 topics identified from the tweets using the LDA model, two were about the COVID-19 vaccines: uptake and supply, respectively. The intensity of the sentiment score for the two topics was associated with the total number of vaccines administered in South Africa (P < 0.001). Discussions regarding the two topics showed higher intensity scores for the neutral sentiment class (P = 0.015) than for other sentiment classes. Additionally, the intensity of the discussions on the two topics was associated with the total number of vaccines administered, new cases, deaths, and recoveries across the three cities (P < 0.001). The sentiment score for the most discussed topic, vaccine uptake, differed across the three cities, with (P = 0.003), (P = 0.002), and (P < 0.001) for positive, negative, and neutral sentiments classes, respectively. The outcome of this research showed that clustered geo-tagged Twitter posts can be used to better analyse the dynamics in sentiments toward community-based infectious diseases-related discussions, such as COVID-19, Malaria, or Monkeypox. This can provide additional city-level information to health policy in planning and decision-making regarding vaccine hesitancy for future outbreaks.

Artificial Intelligence-Based Models for Predicting Vaccines Critical Tweets: An Experimental Study

We studied the suitability of Artificial Intelligence (AI)-based models to predict vaccine-critical tweets on the social media platform Twitter. We manually labeled a sample of 800 tweets as either "vaccine-critical" (i.e, anti-vaccine tweets, mentioned concerns related to vaccine safety and efficacy, and are against vaccine mandates or vaccine passports) or "other" (i.e., tweets that are neutral, report news, or are ambiguous) and used them to train and test AI-based models for automatically predicting vaccine-critical tweets. We fine-tuned two pre-trained deep learning-based language models, BERT and BERTweet, and implemented four classical AI-based models, Random Forest, Logistics Regression, Linear Support Vector Machines, and Multinomial Naïve Bayes. We evaluated these AI-based models using f1 score, accuracy, precision, and recall in three-fold cross-validation. We found that BERTweet outperformed all other models using these measures.

Popular and Scientific Discourse on Autism: Representational Cross-Cultural Analysis of Epistemic Communities to Inform Policy and Practice

Background

Social media provide a window onto the circulation of ideas in everyday folk psychiatry, revealing the themes and issues discussed both by the public and by various scientific communities.

Objective

This study explores the trends in health information about autism spectrum disorder within popular and scientific communities through the systematic semantic exploration of big data gathered from Twitter and PubMed.

Methods

First, we performed a natural language processing by text-mining analysis and with unsupervised (machine learning) topic modeling on a sample of the last 10,000 tweets in English posted with the term #autism (January 2021). We built a network of words to visualize the main dimensions representing these data. Second, we performed precisely the same analysis with all the articles using the term “autism” in PubMed without time restriction. Lastly, we compared the results of the 2 databases.

Results

We retrieved 121,556 terms related to autism in 10,000 tweets and 5.7x109 terms in 57,121 biomedical scientific articles. The 4 main dimensions extracted from Twitter were as follows: integration and social support, understanding and mental health, child welfare, and daily challenges and difficulties. The 4 main dimensions extracted from PubMed were as follows: diagnostic and skills, research challenges, clinical and therapeutical challenges, and neuropsychology and behavior.

Conclusions

This study provides the first systematic and rigorous comparison between 2 corpora of interests, in terms of lay representations and scientific research, regarding the significant increase in information available on autism spectrum disorder and of the difficulty to connect fragments of knowledge from the general population. The results suggest a clear distinction between the focus of topics used in the social media and that of scientific communities. This distinction highlights the importance of knowledge mobilization and exchange to better align research priorities with personal concerns and to address dimensions of well-being, adaptation, and resilience. Health care professionals and researchers can use these dimensions as a framework in their consultations to engage in discussions on issues that matter to beneficiaries and develop clinical approaches and research policies in line with these interests. Finally, our study can inform policy makers on the health and social needs and concerns of individuals with autism and their caregivers, especially to define health indicators based on important issues for beneficiaries.

Sentiment and emotion trends in nurses' tweets about the COVID-19 pandemic

PURPOSE

Twitter is being increasingly used by nursing professionals to share ideas, information, and opinions about the global pandemic, yet there continues to be a lack of research on how nurse sentiment is associated with major events happening on the frontline. The purpose of the study was to quantitatively identify sentiments, emotions, and trends in nurses' tweets and to explore the variations in sentiments and emotions over a period in 2020 with respect to the number of cases and deaths of COVID-19 worldwide.

DESIGN

A cross-sectional data mining study was held from March 3, 2020 through December 3, 2020. The tweets related to COVID-19 were downloaded using the tweet IDs available from a public website. Data were processed and filtered by searching for keywords related to nursing in the profile description field using the R software and JMP Pro Version 16 and the sentiment analysis of each tweet was done using AFINN, Bing, and NRC lexicon.

FINDINGS

A total of 13,868 tweets from the Twitter accounts of self-identified nurses were included in the final analysis. The sentiment scores of nurses' tweets fluctuated over time and some clear patterns emerged related to the number of COVID-19 cases and deaths. Joy decreased and sadness increased over time as the pandemic impacts increased.

CONCLUSIONS

Our study shows that Twitter data can be leveraged to study the emotions and sentiments of nurses, and the findings suggest that the emotional realm of nurses was affected during the COVID-19 pandemic according to the emotional trends observed in tweets.

CLINICAL RELEVANCE

The study provides insight into what nurses are feeling, and findings from this study highlight the importance of developing and implementing interventions targeted at nurses at the workplace to prevent mental health consequences.

Discussions of Asperger Syndrome on Social Media: Content and Sentiment Analysis on Twitter

Background

On May 8, 2021, Elon Musk, a well-recognized entrepreneur and business magnate, revealed on a popular television show that he has Asperger syndrome. Research has shown that people’s perceptions of a condition are modified when influential individuals in society publicly disclose their diagnoses. It was anticipated that Musk's disclosure would contribute to discussions on the internet about the syndrome, and also to a potential change in the perception of this condition.

Objective

The objective of this study was to compare the types of information contained in popular tweets about Asperger syndrome as well as their engagement and sentiment before and after Musk’s disclosure.

Methods

We extracted tweets that were published 1 week before and after Musk's disclosure that had received >30 likes and included the terms “Aspergers” or “Aspie.” The content of each post was classified by 2 independent coders as to whether the information provided was valid, contained misinformation, or was neutral. Furthermore, we analyzed the engagement on these posts and the expressed sentiment by using the AFINN sentiment analysis tool.

Results

We extracted a total of 227 popular tweets (34 posted the week before Musk’s announcement and 193 posted the week after). We classified 210 (92.5%) of the tweets as neutral, 13 (5.7%) tweets as informative, and 4 (1.8%) as containing misinformation. Both informative and misinformative tweets were posted after Musk’s disclosure. Popular tweets posted before Musk’s disclosure were significantly more engaging (received more comments, retweets, and likes) than the tweets posted the week after. We did not find a significant difference in the sentiment expressed in the tweets posted before and after the announcement.

Conclusions

The use of social media platforms by health authorities, autism associations, and other stakeholders has the potential to increase the awareness and acceptance of knowledge about autism and Asperger syndrome. When prominent figures disclose their diagnoses, the number of posts about their particular condition tends to increase and thus promote a potential opportunity for greater outreach to the general public about that condition.

COVID-19 Vaccine Hesitancy: Analysing Twitter to Identify Barriers to Vaccination in a Low Uptake Region of the UK

To facilitate effective targeted COVID-19 vaccination strategies, it is important to understand reasons for vaccine hesitancy where uptake is low. Artificial intelligence (AI) techniques offer an opportunity for real-time analysis of public attitudes, sentiments, and key discussion topics from sources of soft-intelligence, including social media data. In this work, we explore the value of soft-intelligence, leveraged using AI, as an evidence source to support public health research. As a case study, we deployed a natural language processing (NLP) platform to rapidly identify and analyse key barriers to vaccine uptake from a collection of geo-located tweets from London, UK. We developed a search strategy to capture COVID-19 vaccine related tweets, identifying 91,473 tweets between 30 November 2020 and 15 August 2021. The platform's algorithm clustered tweets according to their topic and sentiment, from which we extracted 913 tweets from the top 12 negative sentiment topic clusters. These tweets were extracted for further qualitative analysis. We identified safety concerns; mistrust of government and pharmaceutical companies; and accessibility issues as key barriers limiting vaccine uptake. Our analysis also revealed widespread sharing of vaccine misinformation amongst Twitter users. This study further demonstrates that there is promising utility for using off-the-shelf NLP tools to leverage insights from social media data to support public health research. Future work to examine where this type of work might be integrated as part of a mixed-methods research approach to support local and national decision making is suggested.

COVID-19 Tweet Links: A Preliminary Investigation of Type and Relevance

We conducted an exploratory study of the links found in Twitter tweets. Our results showed that the largest category of tweet links was social media platforms followed by alternative news sites. Government agencies and educational institutions were under-represented. In terms of relevance, about 75% of the links were related to COVID-19 but disappointingly, only 40% of the links were directly related to their respective tweets' topics.

Examining Public Sentiments and Attitudes Toward COVID-19 Vaccination: Infoveillance Study Using Twitter Posts

Background

A global rollout of vaccinations is currently underway to mitigate and protect people from the COVID-19 pandemic. Several individuals have been using social media platforms such as Twitter as an outlet to express their feelings, concerns, and opinions about COVID-19 vaccines and vaccination programs. This study examined COVID-19 vaccine–related tweets from January 1, 2020, to April 30, 2021, to uncover the topics, themes, and variations in sentiments of public Twitter users.

Objective

The aim of this study was to examine key themes and topics from COVID-19 vaccine–related English tweets posted by individuals, and to explore the trends and variations in public opinions and sentiments.

Methods

We gathered and assessed a corpus of 2.94 million COVID-19 vaccine–related tweets made by 1.2 million individuals. We used CoreX topic modeling to explore the themes and topics underlying the tweets, and used VADER sentiment analysis to compute sentiment scores and examine weekly trends. We also performed qualitative content analysis of the top three topics pertaining to COVID-19 vaccination.

Results

Topic modeling yielded 16 topics that were grouped into 6 broader themes underlying the COVID-19 vaccination tweets. The most tweeted topic about COVID-19 vaccination was related to vaccination policy, specifically whether vaccines needed to be mandated or optional (13.94%), followed by vaccine hesitancy (12.63%) and postvaccination symptoms and effects (10.44%) Average compound sentiment scores were negative throughout the 16 weeks for the topics postvaccination symptoms and side effects and hoax/conspiracy. However, consistent positive sentiment scores were observed for the topics vaccination disclosure, vaccine efficacy, clinical trials and approvals, affordability, regulation, distribution and shortage, travel, appointment and scheduling, vaccination sites, advocacy, opinion leaders and endorsement, and gratitude toward health care workers. Reversal in sentiment scores in a few weeks was observed for the topics vaccination eligibility and hesitancy.

Conclusions

Identification of dominant themes, topics, sentiments, and changing trends about COVID-19 vaccination can aid governments and health care agencies to frame appropriate vaccination programs, policies, and rollouts.

Users opinion and emotion understanding in social media regarding COVID-19 vaccine

Online social platforms or social platforms such as Twitter, Facebook and Instagram have become popular platforms for a public discussion about social topics. Recent studies show that there is a growing tendency for people to talk about COVID-19 pandemic in these online channels. The rapid growth of the infected cases by COVID-19 pandemic makes a lots of anxiety and fear among people. With the recent released of Pfizer vaccine, people start posting a lot of rumors regarding the safety concerns of the vaccine, especially among the elderly people. The aim of this study is to bring out the fact that tweets containing all pertinent details about the COVID-19 vaccine and provides an analysis and understanding of users emotions regarding the recent release of COVID-19 vaccine. This study starts with the collection of tweets related to COVID-19 vaccine and then cleaning the dataset from redundant tweets. In this study, we use Twitter API and Web Scraping techniques to obtain a sample of 50,000 tweets talking about COVID-19 vaccine.Further, The analysis of users emotions is achieved by manually labeling and classifying the tweets to either positive or negative. Then, a deep learning based model is used to train the data and classify the people opinion about COVID-19 vaccine. The experimental results illustrate that high percentage of people have shown a positive attitude towards COVID1-19 vaccine. The proposed method is validated over Twitter datasets and the results also demonstrate that use of deep learning classifier can successfully improve the accuracy of people emotions analysis with an accuracy up to 98% for training set and the accuracy for testing set is 73%.

Examining Twitter Discourse on Electronic Cigarette and Tobacco Consumption During National Cancer Prevention Month in 2018: Topic Modeling and Geospatial Analysis

Background

Examining public perception of tobacco products is critical for effective tobacco policy making and public education outreach. While the link between traditional tobacco products and lung cancer is well established, it is not known how the public perceives the association between electronic cigarettes (e-cigarettes) and lung cancer. In addition, it is unclear how members of the public interact with official messages during cancer campaigns on tobacco consumption and lung cancer.

Objective

In this study, we aimed to analyze e-cigarette and smoking tweets in the context of lung cancer during National Cancer Prevention Month in 2018 and examine how e-cigarette and traditional tobacco product discussions relate to implementation of tobacco control policies across different states in the United States.

Methods

We mined tweets that contained the term “lung cancer” on Twitter from February to March 2018. The data set contained 13,946 publicly available tweets that occurred during National Cancer Prevention Month (February 2018), and 10,153 tweets that occurred during March 2018. E-cigarette–related and smoking-related tweets were retrieved, using topic modeling and geospatial analysis.

Results

Debates on harmfulness (454/915, 49.7%), personal experiences (316/915, 34.5%), and e-cigarette risks (145/915, 15.8%) were the major themes of e-cigarette tweets related to lung cancer. Policy discussions (2251/3870, 58.1%), smoking risks (843/3870, 21.8%), and personal experiences (776/3870, 20.1%) were the major themes of smoking tweets related to lung cancer. Geospatial analysis showed that discussion on e-cigarette risks was positively correlated with the number of state-level smoke-free policies enacted for e-cigarettes. In particular, the number of indoor and on campus smoke-free policies was related to the number of tweets on e-cigarette risks (smoke-free indoor, r49=0.33, P=.02; smoke-free campus, r49=0.32, P=.02). The total number of e-cigarette policies was also positively related to the number of tweets on e-cigarette risks (r49=0.32, P=.02). In contrast, the number of smoking policies was not significantly associated with any of the smoking themes in the lung cancer discourse (P>.13).

Conclusions

Though people recognized the importance of traditional tobacco control policies in reducing lung cancer incidences, their views on e-cigarette risks were divided, and discussions on the importance of e-cigarette policy control were missing from public discourse. Findings suggest the need for health organizations to continuously engage the public in discussions on the potential health risks of e-cigarettes and raise awareness of the insidious lobbying efforts from the tobacco industry.

Finding Similar Tweets in Health Related Topics

Social networks have become a very important means to facilitate the creation and sharing of information. They also provide real-time information on sales, marketing, politics, natural disasters, and crisis situations, among others. In this work, we investigate neural models for text similarity that can be used to: 1) determine if messages are related or not with a disease, 2) group similar messages to those that we have already captured, analyzed or stored, and 3) find similarity indices between messages using different learning algorithms. Our results show that we can achieve 90% accuracy on the task of classifying which of two tweets is more similar to a sample tweet.

Twitter and Radiology: Everything You Wanted to Know About #RadTwitter But Were Afraid to Ask

OBJECTIVE

Twitter is one of the world's leading social media platforms, and the most popular such forum for medical professionals. We previously examined how Twitter is used in radiology and suggested methods of optimizing Twitter for radiology education. Here we address those in the radiology community who have not yet embraced Twitter or those who have just begun, offering insights or hacks to make the reader more comfortable with initiating or better leveraging a Twitter account to enhance their radiology work lives.

MATERIAL AND METHODS

We analyzed our Twitter account (@ctisus), dedicated to radiology education and based in the Russell H. Morgan Department of Radiology and Radiological Science at Johns Hopkins Hospital, to ascertain how we could best use the platform for radiology education. We also used the healthcare social media monitoring website Symplur to track the use of 7 radiology-related hashtags from March 6 to April 4, 2021.

RESULTS

Over the 30-day period, we found that #radiology was used 12,311 times; #RadRes (radiology residents) was used 7864 times; #IRad (interventional radiology) was used 6176 times; #FOAMrad (free and open access radiology education) was used 3661 times; #medicalimaging was used 3317 times; #RadTwitter (radiology Twitter) was used 942 times; and #RadEd (radiology education) was used 697 times. This collection of 7 keywords is among the most popularly used by the radiology community.

CONCLUSIONS

Our experience suggests that the radiology community is on Twitter to enhance radiology education. Twitter may seem to be a daunting field of misinformation, but radiologists as well as radiology fellows and residents worldwide have found it to be a platform rich with information and opportunity. Twitter allows information and media to be sent instantly throughout the world. We encourage those in the radiology world not yet or barely using Twitter to get started or more involved in this useful and popular social media platform.

Suicide-related Twitter Content in Response to a National Mental Health Awareness Campaign and the Association between the Campaign and Suicide Rates in Ontario

OBJECTIVE

Mental health awareness (MHA) campaigns have been shown to be successful in improving mental health literacy, decreasing stigma, and generating public discussion. However, there is a dearth of evidence regarding the effects of these campaigns on behavioral outcomes such as suicides. Therefore, the objective of this article is to characterize the association between the event and suicide in Canada's most populous province and the content of suicide-related tweets referencing a Canadian MHA campaign (Bell Let's Talk Day [BLTD]).

METHODS

Suicide counts during the week of BTLD were compared to a control window (2011 to 2016) to test for associations between the BLTD event and suicide. Suicide tweets geolocated to Ontario, posted in 2016 with the BLTD hashtag were coded for specific putatively harmful and protective content.

RESULTS

There was no associated change in suicide counts. Tweets (n = 3,763) mainly included content related to general comments about suicide death (68%) and suicide being a problem (42.8%) with little putatively helpful content such as stories of resilience (0.6%) and messages of hope (2.2%).

CONCLUSIONS

In Ontario, this national mental health media campaign was associated with a high volume of suicide-related tweets but not necessarily including content expected to diminish suicide rates. Campaigns like BLTD should strongly consider greater attention to suicide-related messaging that promotes help-seeking and resilience. This may help to further decrease stigmatization, and potentially, reduce suicide rates.

A Comparative Study on Distancing, Mask and Vaccine Adoption Rates from Global Twitter Trends

COVID-19 is a global health emergency that has fundamentally altered human life. Public perception about COVID-19 greatly informs public policymaking and charts the course of present and future mitigation strategies. Existing approaches to gain insights into the evolving nature of public opinion has led to the application of natural language processing on public interaction data acquired from online surveys and social media. In this work, we apply supervised and unsupervised machine learning approaches on global Twitter data to learn the opinions about adoption of mitigation strategies such as social distancing, masks, and vaccination, as well as the effect of socioeconomic, demographic, political, and epidemiological features on perceptions. Our study reveals the uniform polarity in public sentiment on the basis of spatial proximity or COVID-19 infection rates. We show the reservation about the adoption of social distancing and vaccination across the world and also quantify the influence of airport traffic, homelessness, followed by old age and race on sentiment of netizens within the US.

"Care is not care if it isn't person-centred": A content analysis of how Person-Centred Care is expressed on Twitter

Background

Person‐Centred Care (PCC) has been the subject of growing interest in recent decades. Even though there is no conceptual consensus regarding PCC, many health‐care institutions have implemented elements into their care.

Objective

This study aimed to investigate the PCC topics presented by different stakeholder groups on Twitter and to explore the perceptions of PCC within the content of the tweets.

Method

Tweets with mentions of PCC in various translations were collected through a Twitter Application Programming Interface in October 2019. The tweets were analysed using quantitative and qualitative content analysis.

Results

Five stakeholder groups and ten topics were identified within 1540 tweets. The results showed that the PCC content focused on providing information and opinions rather than expressing experiences of PCC in practice. Qualitative content analysis of 428 selected tweets revealed content on a vision that all care should be person‐centred but that the realization of that vision was more complicated.

Conclusions

Twitter has shown to be a quick and non‐intrusive data collection tool for uncovering stakeholders' expressions concerning PCC. The PCC content revealed that stakeholders feel a need to 'educate' others about their perception of PCC when experiences and real‐life applications are missing. More action should be taken for the implementation of PCC rather than circulating PCC vision without operationalization in care.

Public Contribution

The public provided the data through their posts on Twitter, and it is their perception of PCC that is studied here.

Identification of Risk Factors and Symptoms of COVID-19: Analysis of Biomedical Literature and Social Media Data

BACKGROUND

In December 2019, the COVID-19 outbreak started in China and rapidly spread around the world. Lack of a vaccine or optimized intervention raised the importance of characterizing risk factors and symptoms for the early identification and successful treatment of patients with COVID-19.

OBJECTIVE

This study aims to investigate and analyze biomedical literature and public social media data to understand the association of risk factors and symptoms with the various outcomes observed in patients with COVID-19.

METHODS

Through semantic analysis, we collected 45 retrospective cohort studies, which evaluated 303 clinical and demographic variables across 13 different outcomes of patients with COVID-19, and 84,140 Twitter posts from 1036 COVID-19-positive users. Machine learning tools to extract biomedical information were introduced to identify mentions of uncommon or novel symptoms in tweets. We then examined and compared two data sets to expand our landscape of risk factors and symptoms related to COVID-19.

RESULTS

From the biomedical literature, approximately 90% of clinical and demographic variables showed inconsistent associations with COVID-19 outcomes. Consensus analysis identified 72 risk factors that were specifically associated with individual outcomes. From the social media data, 51 symptoms were characterized and analyzed. By comparing social media data with biomedical literature, we identified 25 novel symptoms that were specifically mentioned in tweets but have been not previously well characterized. Furthermore, there were certain combinations of symptoms that were frequently mentioned together in social media.

CONCLUSIONS

Identified outcome-specific risk factors, symptoms, and combinations of symptoms may serve as surrogate indicators to identify patients with COVID-19 and predict their clinical outcomes in order to provide appropriate treatments.

The Relationship Between Suicide-Related Twitter Events and Suicides in Ontario From 2015 to 2016

Background: Many studies have demonstrated suicide contagion through mainstream journalism; however, few have explored suicide-related social media events and their potential relationship to suicide deaths. Aims: To determine whether Twitter events were associated with changes in subsequent suicides. Methods: Suicide-related Twitter events that garnered at least 100 tweets originating in Ontario, Canada (July 1, 2015 to June 30, 2016) were identified and characterized as putatively "harmful" or "innocuous" based on recommendations for responsible media reporting. The number of suicides in Ontario during the peak of each Twitter event and the subsequent 6 days ("exposure window") was compared with suicides occurring during a pre-event period of the same length ("control window"). Results: There were 17 suicide-related Twitter events during the period of study (12 putatively harmful and five putatively innocuous). The number of tweets per event ranged from 121 for "physician-assisted suicide law in Quebec" to 6,202 for the "Attawapiskat suicide crisis." No significant relationship was detected between Twitter events and actual suicides. Notably, a comprehensive examination of the details of Twitter events showed that even the putatively harmful events lacked many of the characteristics commonly associated with contagion. Limitations: This was an uncontrolled experiment in only one epoch and a single Canadian province. Discussion: This study found no evidence of suicide contagion associated with Twitter events. This finding must be interpreted with caution given the relatively innocuous content of suicide-related Tweets in Ontario during 2015-2016.

Cross-Cultural Polarity and Emotion Detection Using Sentiment Analysis and Deep Learning on COVID-19 Related Tweets

How different cultures react and respond given a crisis is predominant in a society's norms and political will to combat the situation. Often, the decisions made are necessitated by events, social pressure, or the need of the hour, which may not represent the nation's will. While some are pleased with it, others might show resentment. Coronavirus (COVID-19) brought a mix of similar emotions from the nations towards the decisions taken by their respective governments. Social media was bombarded with posts containing both positive and negative sentiments on the COVID-19, pandemic, lockdown, and hashtags past couple of months. Despite geographically close, many neighboring countries reacted differently to one another. For instance, Denmark and Sweden, which share many similarities, stood poles apart on the decision taken by their respective governments. Yet, their nation's support was mostly unanimous, unlike the South Asian neighboring countries where people showed a lot of anxiety and resentment. The purpose of this study is to analyze reaction of citizens from different cultures to the novel Coronavirus and people's sentiment about subsequent actions taken by different countries. Deep long short-term memory (LSTM) models used for estimating the sentiment polarity and emotions from extracted tweets have been trained to achieve state-of-the-art accuracy on the sentiment140 dataset. The use of emoticons showed a unique and novel way of validating the supervised deep learning models on tweets extracted from Twitter.

Location Prediction for Tweets

Geographic information provides an important insight into many data mining and social media systems. However, users are reluctant to provide such information due to various concerns, such as inconvenience, privacy, etc. In this paper, we aim to develop a deep learning based solution to predict geographic information for tweets. The current approaches bear two major limitations, including (a) hard to model the long term information and (b) hard to explain to the end users what the model learns. To address these issues, our proposed model embraces three key ideas. First, we introduce a multi-head self-attention model for text representation. Second, to further improve the result on informal language, we treat subword as a feature in our model. Lastly, the model is trained jointly with the city and country to incorporate the information coming from different labels. The experiment performed on W-NUT 2016 Geo-tagging shared task shows our proposed model is competitive with the state-of-the-art systems when using accuracy measurement, and in the meanwhile, leading to a better distance measure over the existing approaches.

Using Twitter to Detect Psychological Characteristics of Self-Identified Persons With Autism Spectrum Disorder: A Feasibility Study

Background

More than 3.5 million Americans live with autism spectrum disorder (ASD). Major challenges persist in diagnosing ASD as no medical test exists to diagnose this disorder. Digital phenotyping holds promise to guide in the clinical diagnoses and screening of ASD.

Objective

This study aims to explore the feasibility of using the Web-based social media platform Twitter to detect psychological and behavioral characteristics of self-identified persons with ASD.

Methods

Data from Twitter were retrieved from 152 self-identified users with ASD and 182 randomly selected control users from March 22, 2012 to July 20, 2017. We conducted a between-group comparative textual analysis of tweets about repetitive and obsessive-compulsive behavioral characteristics typically associated with ASD. In addition, common emotional characteristics of persons with ASD, such as fear, paranoia, and anxiety, were examined between groups through textual analysis. Furthermore, we compared the timing of tweets between users with ASD and control users to identify patterns in communication.

Results

Users with ASD posted a significantly higher frequency of tweets related to the specific repetitive behavior of counting compared with control users (P<.001). The textual analysis of obsessive-compulsive behavioral characteristics, such as fixate, excessive, and concern, were significantly higher among users with ASD compared with the control group (P<.001). In addition, emotional terms related to fear, paranoia, and anxiety were tweeted at a significantly higher rate among users with ASD compared with control users (P<.001). Users with ASD posted a smaller proportion of tweets during time intervals of 00:00-05:59 (P<.001), 06:00-11:59 (P<.001), and 18:00-23.59 (P<.001), as well as a greater proportion of tweets from 12:00 to 17:59 (P<.001) compared with control users.

Conclusions

Social media may be a valuable resource for observing unique psychological characteristics of self-identified persons with ASD. Collecting and analyzing data from these digital platforms may afford opportunities to identify the characteristics of ASD and assist in the diagnosis or verification of ASD. This study highlights the feasibility of leveraging digital data for gaining new insights into various health conditions.

The reliability of tweets as a supplementary method of seasonal influenza surveillance

BACKGROUND

Existing influenza surveillance in the United States is focused on the collection of data from sentinel physicians and hospitals; however, the compilation and distribution of reports are usually delayed by up to 2 weeks. With the popularity of social media growing, the Internet is a source for syndromic surveillance due to the availability of large amounts of data. In this study, tweets, or posts of 140 characters or less, from the website Twitter were collected and analyzed for their potential as surveillance for seasonal influenza.

OBJECTIVE

There were three aims: (1) to improve the correlation of tweets to sentinel-provided influenza-like illness (ILI) rates by city through filtering and a machine-learning classifier, (2) to observe correlations of tweets for emergency department ILI rates by city, and (3) to explore correlations for tweets to laboratory-confirmed influenza cases in San Diego.

METHODS

Tweets containing the keyword "flu" were collected within a 17-mile radius from 11 US cities selected for population and availability of ILI data. At the end of the collection period, 159,802 tweets were used for correlation analyses with sentinel-provided ILI and emergency department ILI rates as reported by the corresponding city or county health department. Two separate methods were used to observe correlations between tweets and ILI rates: filtering the tweets by type (non-retweets, retweets, tweets with a URL, tweets without a URL), and the use of a machine-learning classifier that determined whether a tweet was "valid", or from a user who was likely ill with the flu.

RESULTS

Correlations varied by city but general trends were observed. Non-retweets and tweets without a URL had higher and more significant (P<.05) correlations than retweets and tweets with a URL. Correlations of tweets to emergency department ILI rates were higher than the correlations observed for sentinel-provided ILI for most of the cities. The machine-learning classifier yielded the highest correlations for many of the cities when using the sentinel-provided or emergency department ILI as well as the number of laboratory-confirmed influenza cases in San Diego. High correlation values (r=.93) with significance at P<.001 were observed for laboratory-confirmed influenza cases for most categories and tweets determined to be valid by the classifier.

CONCLUSIONS

Compared to tweet analyses in the previous influenza season, this study demonstrated increased accuracy in using Twitter as a supplementary surveillance tool for influenza as better filtering and classification methods yielded higher correlations for the 2013-2014 influenza season than those found for tweets in the previous influenza season, where emergency department ILI rates were better correlated to tweets than sentinel-provided ILI rates. Further investigations in the field would require expansion with regard to the location that the tweets are collected from, as well as the availability of more ILI data.