The 'who' and 'what' of #diabetes on Twitter

Topic modeling and social network analysis approach to explore diabetes discourse on Twitter in India

Introduction

The utilization of social media presents a promising avenue for the prevention and management of diabetes. To effectively cater to the diabetes-related knowledge, support, and intervention needs of the community, it is imperative to attain a deeper understanding of the extent and content of discussions pertaining to this health issue. This study aims to assess and compare various topic modeling techniques to determine the most effective model for identifying the core themes in diabetes-related tweets, the sources responsible for disseminating this information, the reach of these themes, and the influential individuals within the Twitter community in India.

Methods

Twitter messages from India, dated between 7 November 2022 and 28 February 2023, were collected using the Twitter API. The unsupervised machine learning topic models, namely, Latent Dirichlet Allocation (LDA), non-negative matrix factorization (NMF), BERTopic, and Top2Vec, were compared, and the best-performing model was used to identify common diabetes-related topics. Influential users were identified through social network analysis.

Results

The NMF model outperformed the LDA model, whereas BERTopic performed better than Top2Vec. Diabetes-related conversations revolved around eight topics, namely, promotion, management, drug and personal story, consequences, risk factors and research, raising awareness and providing support, diet, and opinion and lifestyle changes. The influential nodes identified were mainly health professionals and healthcare organizations.

Discussion

The study identified important topics of discussion along with health professionals and healthcare organizations involved in sharing diabetes-related information with the public. Collaborations among influential healthcare organizations, health professionals, and the government can foster awareness and prevent noncommunicable diseases.

Who tweets what about personalised medicine? Promises and concerns from Twitter discussions in Denmark

Digital health data are seen as valuable resources for the development of better and more efficient treatments, for instance through personalised medicine. However, health data are information about individuals who hold opinions and can challenge how data about them are used. Therefore it is important to understand public discussions around reuse of digital health data. Social media have been heralded as enabling new forms of public engagement and as a place to study social issues. In this paper, we study a public debate on Twitter about personalised medicine. We explore who participates in discussions about personalised medicine on Twitter and what they tweet about. Based on user-generated biographies we categorise users as having a 'Professional interest in personalised medicine' or as 'Private' users. We describe how users within the field tweet about the promises of personalised medicine, while users unaffiliated with the field tweet about the concrete realisation of these ambitions in the form of a new infrastructure and express concerns about the conditions for the implementation. Our study serves to remind people interested in public opinion that Twitter is a platform used for multiple purposes by different actors and not simply a bottom-up democratic forum. This study contributes with insights relevant to policymakers wishing to expand infrastructures for reuse of health data. First, by providing insights into what is discussed about health data reuse. Second, by exploring how Twitter can be used as a platform to study public discussions about reuse of health data.

Search Term Identification Methods for Computational Health Communication: Word Embedding and Network Approach for Health Content on YouTube

Background

Common methods for extracting content in health communication research typically involve using a set of well-established queries, often names of medical procedures or diseases, that are often technical or rarely used in the public discussion of health topics. Although these methods produce high recall (ie, retrieve highly relevant content), they tend to overlook health messages that feature colloquial language and layperson vocabularies on social media. Given how such messages could contain misinformation or obscure content that circumvents official medical concepts, correctly identifying (and analyzing) them is crucial to the study of user-generated health content on social media platforms.

Objective

Health communication scholars would benefit from a retrieval process that goes beyond the use of standard terminologies as search queries. Motivated by this, this study aims to put forward a search term identification method to improve the retrieval of user-generated health content on social media. We focused on cancer screening tests as a subject and YouTube as a platform case study.

Methods

We retrieved YouTube videos using cancer screening procedures (colonoscopy, fecal occult blood test, mammogram, and pap test) as seed queries. We then trained word embedding models using text features from these videos to identify the nearest neighbor terms that are semantically similar to cancer screening tests in colloquial language. Retrieving more YouTube videos from the top neighbor terms, we coded a sample of 150 random videos from each term for relevance. We then used text mining to examine the new content retrieved from these videos and network analysis to inspect the relations between the newly retrieved videos and videos from the seed queries.

Results

The top terms with semantic similarities to cancer screening tests were identified via word embedding models. Text mining analysis showed that the 5 nearest neighbor terms retrieved content that was novel and contextually diverse, beyond the content retrieved from cancer screening concepts alone. Results from network analysis showed that the newly retrieved videos had at least one total degree of connection (sum of indegree and outdegree) with seed videos according to YouTube relatedness measures.

Conclusions

We demonstrated a retrieval technique to improve recall and minimize precision loss, which can be extended to various health topics on YouTube, a popular video-sharing social media platform. We discussed how health communication scholars can apply the technique to inspect the performance of the retrieval strategy before investing human coding resources and outlined suggestions on how such a technique can be extended to other health contexts.

Identifying Patients With Inflammatory Bowel Disease on Twitter and Learning From Their Personal Experience: Retrospective Cohort Study

Background

Patients use social media as an alternative information source, where they share information and provide social support. Although large amounts of health-related data are posted on Twitter and other social networking platforms each day, research using social media data to understand chronic conditions and patients’ lifestyles is limited.

Objective

In this study, we contributed to closing this gap by providing a framework for identifying patients with inflammatory bowel disease (IBD) on Twitter and learning from their personal experiences. We enabled the analysis of patients’ tweets by building a classifier of Twitter users that distinguishes patients from other entities. This study aimed to uncover the potential of using Twitter data to promote the well-being of patients with IBD by relying on the wisdom of the crowd to identify healthy lifestyles. We sought to leverage posts describing patients’ daily activities and their influence on their well-being to characterize lifestyle-related treatments.

Methods

In the first stage of the study, a machine learning method combining social network analysis and natural language processing was used to automatically classify users as patients or not. We considered 3 types of features: the user’s behavior on Twitter, the content of the user’s tweets, and the social structure of the user’s network. We compared the performances of several classification algorithms within 2 classification approaches. One classified each tweet and deduced the user’s class from their tweet-level classification. The other aggregated tweet-level features to user-level features and classified the users themselves. Different classification algorithms were examined and compared using 4 measures: precision, recall, F1 score, and the area under the receiver operating characteristic curve. In the second stage, a classifier from the first stage was used to collect patients' tweets describing the different lifestyles patients adopt to deal with their disease. Using IBM Watson Service for entity sentiment analysis, we calculated the average sentiment of 420 lifestyle-related words that patients with IBD use when describing their daily routine.

Results

Both classification approaches showed promising results. Although the precision rates were slightly higher for the tweet-level approach, the recall and area under the receiver operating characteristic curve of the user-level approach were significantly better. Sentiment analysis of tweets written by patients with IBD identified frequently mentioned lifestyles and their influence on patients’ well-being. The findings reinforced what is known about suitable nutrition for IBD as several foods known to cause inflammation were pointed out in negative sentiment, whereas relaxing activities and anti-inflammatory foods surfaced in a positive context.

Conclusions

This study suggests a pipeline for identifying patients with IBD on Twitter and collecting their tweets to analyze the experimental knowledge they share. These methods can be adapted to other diseases and enhance medical research on chronic conditions.

Extraction of Explicit and Implicit Cause-Effect Relationships in Patient-Reported Diabetes-Related Tweets From 2017 to 2021: Deep Learning Approach

Background

Intervening in and preventing diabetes distress requires an understanding of its causes and, in particular, from a patient’s perspective. Social media data provide direct access to how patients see and understand their disease and consequently show the causes of diabetes distress.

Objective

Leveraging machine learning methods, we aim to extract both explicit and implicit cause-effect relationships in patient-reported diabetes-related tweets and provide a methodology to better understand the opinions, feelings, and observations shared within the diabetes online community from a causality perspective.

Methods

More than 30 million diabetes-related tweets in English were collected between April 2017 and January 2021. Deep learning and natural language processing methods were applied to focus on tweets with personal and emotional content. A cause-effect tweet data set was manually labeled and used to train (1) a fine-tuned BERTweet model to detect causal sentences containing a causal relation and (2) a conditional random field model with Bidirectional Encoder Representations from Transformers (BERT)-based features to extract possible cause-effect associations. Causes and effects were clustered in a semisupervised approach and visualized in an interactive cause-effect network.

Results

Causal sentences were detected with a recall of 68% in an imbalanced data set. A conditional random field model with BERT-based features outperformed a fine-tuned BERT model for cause-effect detection with a macro recall of 68%. This led to 96,676 sentences with cause-effect relationships. “Diabetes” was identified as the central cluster followed by “death” and “insulin.” Insulin pricing–related causes were frequently associated with death.

Conclusions

A novel methodology was developed to detect causal sentences and identify both explicit and implicit, single and multiword cause, and the corresponding effect, as expressed in diabetes-related tweets leveraging BERT-based architectures and visualized as cause-effect network. Extracting causal associations in real life, patient-reported outcomes in social media data provide a useful complementary source of information in diabetes research.

Using Twitter Comments to Understand People's Experiences of UK Health Care During the COVID-19 Pandemic: Thematic and Sentiment Analysis

Background

The COVID-19 pandemic has led to changes in health service utilization patterns and a rapid rise in care being delivered remotely. However, there has been little published research examining patients’ experiences of accessing remote consultations since COVID-19. Such research is important as remote methods for delivering some care may be maintained in the future.

Objective

The aim of this study was to use content from Twitter to understand discourse around health and care delivery in the United Kingdom as a result of COVID-19, focusing on Twitter users’ views on and attitudes toward care being delivered remotely.

Methods

Tweets posted from the United Kingdom between January 2018 and October 2020 were extracted using the Twitter application programming interface. A total of 1408 tweets across three search terms were extracted into Excel; 161 tweets were removed following deduplication and 610 were identified as irrelevant to the research question. The remaining relevant tweets (N=637) were coded into categories using NVivo software, and assigned a positive, neutral, or negative sentiment. To examine views of remote care over time, the coded data were imported back into Excel so that each tweet was associated with both a theme and sentiment.

Results

The volume of tweets on remote care delivery increased markedly following the COVID-19 outbreak. Five main themes were identified in the tweets: access to remote care (n=267), quality of remote care (n=130), anticipation of remote care (n=39), online booking and asynchronous communication (n=85), and publicizing changes to services or care delivery (n=160). Mixed public attitudes and experiences to the changes in service delivery were found. The proportion of positive tweets regarding access to, and quality of, remote care was higher in the immediate period following the COVID-19 outbreak (March-May 2020) when compared to the time before COVID-19 onset and the time when restrictions from the first lockdown eased (June-October 2020).

Conclusions

Using Twitter data to address our research questions proved beneficial for providing rapid access to Twitter users’ attitudes to remote care delivery at a time when it would have been difficult to conduct primary research due to COVID-19. This approach allowed us to examine the discourse on remote care over a relatively long period and to explore shifting attitudes of Twitter users at a time of rapid changes in care delivery. The mixed attitudes toward remote care highlight the importance for patients to have a choice over the type of consultation that best suits their needs, and to ensure that the increased use of technology for delivering care does not become a barrier for some. The finding that overall sentiment about remote care was more positive in the early stages of the pandemic but has since declined emphasizes the need for a continued examination of people’s preference, particularly if remote appointments are likely to remain central to health care delivery.

Re-evaluating standards of human subjects protection for sensitive health data in social media networks

This study addresses ethical questions about conducting health science research using network data from social media platforms. We provide examples of ethically problematic areas related to participant consent, expectation of privacy, and social media networks. Further, to illustrate how researchers can maintain ethical integrity while leveraging social media networks, we describe a study that demonstrates the ability to use social media to identify individuals affected by cancer. We discuss best practices and ethical guidelines for studying social media network data, including data collection, analysis, and reporting.

From Medicine to Health: The Proliferation and Diversification of Cultural Authority

In his account of the medical profession's ascent, Paul Starr drew a distinction between the social authority of physicians and the cultural authority of medicine-between doctors' capacity to direct others' behavior and the ability of medical institutions and discourses to shape meanings of illness, health, wellness, and treatment. Subsequently, scholars have reflected on the social-structural transformations challenging physicians' social authority but neglected shifts in cultural authority. Focusing on the United States, we find a proliferation and diversification of cultural authority, reflecting a partial movement from the domain of medicine into new terrains of health. This shift is apparent in the resurgence of alternative healing, the advent of new forms of self-care and self-monitoring, the rise of health social movements, and the spread of health information online. We advance a research agenda to understand how the mechanisms and dynamics of cultural authority shape contests to speak in the name of health.

Qualitative Content Analysis of Type 1 Diabetes Caregiver Blogs and Correlations With Caregiver Challenges and Successes

Social media increasingly reflects patient experience, especially for self-managed conditions. We examined family experience with type 1 diabetes (T1D) through qualitative analysis of blogs written by caregivers of children with T1D, survey derived from that analysis, and survey administration among T1D caregivers. Analysis of 140 blog posts and 663 associated comments identified 77 topics, which were categorized into self-management, emotional, challenges, and successes. By subcategory analysis, self-management challenges were strongly correlated between blog content and survey responses (R = .838, P = .005), and emotional challenges were moderately correlated (R = .415, P = .02). Emotional successes were not significantly correlated (R = .161, P = .511), and self-management successes were too few to analyze. The range of topics and the correlations between blog expressions and survey responses highlight the potential of blog analysis to gain insight into the challenges facing families living with T1D.

Characterization of Vaccine Tweets During the Early Stage of the COVID-19 Outbreak in the United States: Topic Modeling Analysis

BACKGROUND

During the early stages of the COVID-19 pandemic, developing safe and effective coronavirus vaccines was considered critical to arresting the spread of the disease. News and social media discussions have extensively covered the issue of coronavirus vaccines, with a mixture of vaccine advocacies, concerns, and oppositions.

OBJECTIVE

This study aimed to uncover the emerging themes in Twitter users' perceptions and attitudes toward vaccines during the early stages of the COVID-19 outbreak.

METHODS

This study employed topic modeling to analyze tweets related to coronavirus vaccines at the start of the COVID-19 outbreak in the United States (February 21 to March 20, 2020). We created a predefined query (eg, "COVID" AND "vaccine") to extract the tweet text and metadata (number of followers of the Twitter account and engagement metrics based on likes, comments, and retweeting) from the Meltwater database. After preprocessing the data, we tested Latent Dirichlet Allocation models to identify topics associated with these tweets. The model specifying 20 topics provided the best overall coherence, and each topic was interpreted based on its top associated terms.

RESULTS

In total, we analyzed 100,209 tweets containing keywords related to coronavirus and vaccines. The 20 topics were further collapsed based on shared similarities, thereby generating 7 major themes. Our analysis characterized 26.3% (26,234/100,209) of the tweets as News Related to Coronavirus and Vaccine Development, 25.4% (25,425/100,209) as General Discussion and Seeking of Information on Coronavirus, 12.9% (12,882/100,209) as Financial Concerns, 12.7% (12,696/100,209) as Venting Negative Emotions, 9.9% (9908/100,209) as Prayers and Calls for Positivity, 8.1% (8155/100,209) as Efficacy of Vaccine and Treatment, and 4.9% (4909/100,209) as Conspiracies about Coronavirus and Its Vaccines. Different themes demonstrated some changes over time, mostly in close association with news or events related to vaccine developments. Twitter users who discussed conspiracy theories, the efficacy of vaccines and treatments, and financial concerns had more followers than those focused on other vaccine themes. The engagement level-the extent to which a tweet being retweeted, quoted, liked, or replied by other users-was similar among different themes, but tweets venting negative emotions yielded the lowest engagement.

CONCLUSIONS

This study enriches our understanding of public concerns over new vaccines or vaccine development at early stages of the outbreak, bearing implications for influencing vaccine attitudes and guiding public health efforts to cope with infectious disease outbreaks in the future. This study concluded that public concerns centered on general policy issues related to coronavirus vaccines and that the discussions were considerably mixed with political views when vaccines were not made available. Only a small proportion of tweets focused on conspiracy theories, but these tweets demonstrated high engagement levels and were often contributed by Twitter users with more influence.

The present and future scope of real-world evidence research in diabetes: What questions can and cannot be answered and what might be possible in the future?

The last decade has witnessed an exponential growth in the opportunities to collect and link health-related data from multiple resources, including primary care, administrative, and device data. The availability of these "real-world," "big data" has fuelled also an intense methodological research into methods to handle them and extract actionable information. In medicine, the evidence generated from "real-world data" (RWD), which are not purposely collected to answer biomedical questions, is commonly termed "real-world evidence" (RWE). In this review, we focus on RWD and RWE in the area of diabetes research, highlighting their contributions in the last decade; and give some suggestions for future RWE diabetes research, by applying well-established and less-known tools to direct RWE diabetes research towards better personalized approaches to diabetes care. We underline the essential aspects to consider when using RWD and the key features limiting the translational potential of RWD in generating high-quality and applicable RWE. Only if viewed in the context of other study designs and statistical methods, with its pros and cons carefully considered, RWE will exploit its full potential as a complementary or even, in some cases, substitutive source of evidence compared to the expensive evidence obtained from randomized controlled trials.

Who Tweets About Diabetic Foot on Twitter and Which Tweets Are More Attractive?

Diabetic foot is a serious problem for health care systems. Twitter can provide communication between people and it might be an informative tool for health care management. The purpose of this study is detecting the people or organizations that tweet about diabetic foot and analyze the interactions of these tweets on Twitter. All tweets containing the keyword “diabetic foot” in April 2019 were collected. The users were separated into 7 groups: patients with diabetes, health care providers, nongovernmental organizations, information sites and communication media, private companies, medical students, and others. Health care professionals and nonprofessionals were evaluated in likes, mentions, and retweets. The major group was health care providers. By 2-group comparisons of professionals and nonprofessionals, all likes, mentions, and retweets were significantly different ( P = .02, P = .04, P < .001, respectively). We concluded that the tweets of health care professionals get more interaction than others. Twitter might be a useful tool to distinguish accurate information about diabetic foot. Also, health care professionals should use for making people aware of the diabetic foot and shed light on society.

Big Data, Computational Social Science, and Health Communication: A Review and Agenda for Advancing Theory

Contemporary research on health communication has been marked by the presence of big data and computational social science (CSS) techniques. The relative novelty of these approaches makes it worthwhile to consider their status and potential for advancing health communication scholarship. This essay offers an introduction focusing on how big data and CSS techniques are being employed to study health communication and their utility for theory development. Key trends in this body of research are summarized, including the use of big data and CSS for examining public perceptions of health conditions or events, investigating network-related dimensions of health phenomena, and illness monitoring. The implications of big data and CSS for health communication theory are also evaluated. Opportunities presented by big data and CSS to help extend existing theories and build new communication theories are discussed.

Diabetes on Twitter: A Sentiment Analysis

BACKGROUND

Contents published on social media have an impact on individuals and on their decision making. Knowing the sentiment toward diabetes is fundamental to understanding the impact that such information could have on people affected with this health condition and their family members. The objective of this study is to analyze the sentiment expressed in messages on diabetes posted on Twitter.

METHOD

Tweets including one of the terms "diabetes," "t1d," and/or "t2d" were extracted for one week using the Twitter standard API. Only the text message and the number of followers of the users were extracted. The sentiment analysis was performed by using SentiStrength.

RESULTS

A total of 67 421 tweets were automatically extracted, of those 3.7% specifically referred to T1D; and 6.8% specifically mentioned T2D. One or more emojis were included in 7.0% of the posts. Tweets specifically mentioning T2D and that did not include emojis were significantly more negative than the tweets that included emojis (-2.22 vs -1.48, P < .001). Tweets on T1D and that included emojis were both significantly more positive and also less negative than tweets without emojis (1.71 vs 1.49 and -1.31 vs -1.50, respectively; P < .005). The number of followers had a negative association with positive sentiment strength ( r = -.023, P < .001) and a positive association with negative sentiment ( r = .016, P < .001).

CONCLUSION

The use of sentiment analysis techniques on social media could increase our knowledge of how social media impact people with diabetes and their families and could help to improve public health strategies.

State of the Science: A Scoping Review and Gap Analysis of Diabetes Online Communities

BACKGROUND

Individuals with diabetes are using online resources to engage in diabetes online communities to find diabetes-related support and information. The benefits and consequences of DOC (diabetes online community) use are unclear. This scoping review aims to map existing research focused on organic DOCs in which individuals affected by diabetes are interacting with peers.

METHOD

A scoping review was conducted to comprehensively report and synthesize relevant literature published prior to 2018. Attention was paid to variations in study design, DOC user and platform characteristics, and potential or actual benefits and consequences.

RESULTS

Of the 14 486 titles identified, 47 articles met the inclusion criteria and were included in this scoping review. No overt definition of the DOC could be identified. Perceived or actual benefits associated with DOC use can be broadly categorized as clinical, behavioral, psychosocial and community outcomes. Perceived, potential, or actual consequences associated with DOC use were categorized as quality of information, risky behavior exploration, acute concerns, psychosocial, privacy, and inactivity.

CONCLUSIONS

The results of this review strongly suggest DOC use is highly beneficial with relatively few negative consequences. DOC use is an emerging area of research and research gaps exist. Future research should seek to identify benefits and consequences to DOC use in experimental trials.

Integrating sentiment and social structure to determine preference alignments: the Irish Marriage Referendum

We examine the relationship between social structure and sentiment through the analysis of a large collection of tweets about the Irish Marriage Referendum of 2015. We obtain the sentiment of every tweet with the hashtags #marref and #marriageref that was posted in the days leading to the referendum, and construct networks to aggregate sentiment and use it to study the interactions among users. Our analysis shows that the sentiment of outgoing mention tweets is correlated with the sentiment of incoming mentions, and there are significantly more connections between users with similar sentiment scores than among users with opposite scores in the mention and follower networks. We combine the community structure of the follower and mention networks with the activity level of the users and sentiment scores to find groups that support voting 'yes' or 'no' in the referendum. There were numerous conversations between users on opposing sides of the debate in the absence of follower connections, which suggests that there were efforts by some users to establish dialogue and debate across ideological divisions. Our analysis shows that social structure can be integrated successfully with sentiment to analyse and understand the disposition of social media users around controversial or polarizing issues. These results have potential applications in the integration of data and metadata to study opinion dynamics, public opinion modelling and polling.

Toward Precision Healthcare: Context and Mathematical Challenges

Precision medicine refers to the idea of delivering the right treatment to the right patient at the right time, usually with a focus on a data-centered approach to this task. In this perspective piece, we use the term "precision healthcare" to describe the development of precision approaches that bridge from the individual to the population, taking advantage of individual-level data, but also taking the social context into account. These problems give rise to a broad spectrum of technical, scientific, policy, ethical and social challenges, and new mathematical techniques will be required to meet them. To ensure that the science underpinning "precision" is robust, interpretable and well-suited to meet the policy, ethical and social questions that such approaches raise, the mathematical methods for data analysis should be transparent, robust, and able to adapt to errors and uncertainties. In particular, precision methodologies should capture the complexity of data, yet produce tractable descriptions at the relevant resolution while preserving intelligibility and traceability, so that they can be used by practitioners to aid decision-making. Through several case studies in this domain of precision healthcare, we argue that this vision requires the development of new mathematical frameworks, both in modeling and in data analysis and interpretation.