Understanding Demographic Bias and Representation in Social Media Health Data

Abstract. This article is the result of a campaign done during the COVID-19 lockdown in Catalonia. The Television of Catalonia audience was involved in an action to inform about the weather from their own homes by posting Twitter videos. Some of the videos were shown on air in the weather segment of the television station's main news programs. We have correlated participation in the campaign with meteorological and public health data and found that weather is related to the mood of people when using social media platforms such as Twitter.

Download Full-text

HEALTH DEBATES ON SOCIAL MEDIA: LINKING DIGITAL HEALTH TO COMMUNICATION AND AI STUDIES

AoIR Selected Papers of Internet Research ◽

10.5210/spir.v2020i0.11268 ◽

2020 ◽

Author(s):

Martina Skrubbeltrang Mahnke ◽

Katrine Meldgaard Kjær

Keyword(s):

Social Media ◽

Communication Theory ◽

Digital Health ◽

Theoretical Perspective ◽

Health Data ◽

Digital Data ◽

Analytical Strategies ◽

Health Studies ◽

Theoretical Question ◽

Media Data

Drawing on the examples of three current health debates on Twitter revolving around the hashtags #medicalcannabis, #covid19 and #vaccinationervirker (in English: vaccinations work), this paper explores the broader theoretical question how we may expand the notion of ‘health data’ to include health debates and discussions on social media, and further how these can be linked to concepts of digital health data assemblages and communicative others. By combing insights from AI and communication studies and STS, as well as insights into the human-data relationship from digital health studies, the paper theoretically links digital data assemblages with communication theory which provides tools to think about health data as relational and communicative. With this, social media data becomes relevant in a new light, not only for media scientists, but also for understanding health practices in a digital age more generally. The paper discusses issues this theoretical perspective raises for researchers of social media and online health engagement; what challenges and possibilities this provides in relation to studying social media discussions on health; and finally, an overview of analytical strategies and empirical fields from which these perspectives may be studied.

Download Full-text

COVID-19 pandemic impact on people with rheumatic and musculoskeletal diseases: Insights from patient-generated health data on social media

Rheumatology ◽

10.1093/rheumatology/keab174 ◽

2021 ◽

Author(s):

Katja Reuter ◽

Atul Deodhar ◽

Souzi Makri ◽

Michael Zimmer ◽

Francis Berenbaum ◽

...

Keyword(s):

Social Media ◽

Real Time ◽

Health Behaviour ◽

Lupus Erythematosus ◽

Negative Impact ◽

Musculoskeletal Diseases ◽

Health Data ◽

Physical And Mental Health ◽

Convenience Sample ◽

The Impact

Abstract Objectives During the COVID-19 pandemic, much communication occurred online, through social media. This study aimed to provide patient perspective data on how the COVID-19 pandemic impacted people with rheumatic and musculoskeletal diseases (RMDs), using Twitter-based patient-generated health data (PGHD). Methods A convenience sample of Twitter messages in English posted by people with RMDs was extracted between March 1, and July 12, 2020 and examined using thematic analysis. Included were Twitter messages that mentioned keywords and hashtags related to both COVID-19 (or SARS-CoV-2) and select RMDs. The RMDs monitored included inflammatory-driven (joint) conditions (Ankylosing Spondylitis, Rheumatoid Arthritis, Psoriatic Arthritis, Lupus/Systemic Lupus Erythematosus, and Gout). Results The analysis included 569 tweets by 375 Twitter users with RMDs across several countries. Eight themes emerged regarding the impact of the COVID-19 pandemic on people with RMDs: (1) lack of understanding of SARS-CoV-2/COVID-19; (2) critical changes in health behaviour; (3) challenges in healthcare practice and communication with healthcare professionals; (4) difficulties with access to medical care; (5) negative impact on physical and mental health, coping strategies; (6) issues around work participation, (7) negative effects of the media; (8) awareness-raising. Conclusion The findings show that Twitter serves as a real-time data source to understand the impact of the COVID-19 pandemic on people with RMDs. The platform provided “early signals” of potentially critical health behaviour changes. Future epidemics might benefit from the real-time use of Twitter-based PGHD to identify emerging health needs, facilitate communication, and inform clinical practice decisions.

Download Full-text

SocInf: Membership Inference Attacks on Social Media Health Data With Machine Learning

IEEE Transactions on Computational Social Systems ◽

10.1109/tcss.2019.2916086 ◽

2019 ◽

Vol 6 (5) ◽

pp. 907-921 ◽

Cited By ~ 5

Author(s):

Gaoyang Liu ◽

Chen Wang ◽

Kai Peng ◽

Haojun Huang ◽

Yutong Li ◽

...

Keyword(s):

Machine Learning ◽

Social Media ◽

Health Data ◽

Inference Attacks

Download Full-text

#Datasaveslives: mixed methods analysis of a social media campaign to promote the benefits of using health data for research purposes (Preprint)

10.2196/preprints.16348 ◽

2019 ◽

Author(s):

Lamiece Hassan ◽

Goran Nenadic ◽

Mary Patricia Tully

Keyword(s):

Social Media ◽

Health Informatics ◽

Data Science ◽

Health Data ◽

Media Campaign ◽

Wide Audience ◽

Personal Support ◽

Twitter Users ◽

The Uk ◽

The Impact

BACKGROUND Social media provides the potential to engage a wide audience about scientific research, including the public. However little empirical research exists to guide health scientists regarding what works and how to optimize impact. We examined the social media campaign #datasaveslives, which was established in 2014 to highlight positive examples of the use and reuse of health data in research. OBJECTIVE The study aimed to examine how the #datasaveslives hashtag was used on social media, how often and by whom; thus, the study aimed to provide insights into the impact of a major social media campaign in the UK health informatics research community and further afield. METHODS We analyzed all publicly available posts (tweets) between 1 September 2016 and 31 August 2017 on the microblogging platform Twitter that included the hashtag #datasaveslives (n=13,895). Using a combination of qualitative and quantitative analyses, we determined the frequency and purpose of tweets. Social network analysis was used to analyze and visualize tweet sharing (‘retweet’) networks among hashtag users. RESULTS Overall, we found 4,175 original tweets and 9,720 retweets featuring #datasaveslives by 3,649 unique Twitter users. In total, 2,756 (66.0%) of original posts were retweeted at least once. Higher frequencies of tweets were observed during the weeks of prominent policy publications, popular conferences and public engagement events. Cluster analysis based on retweet relationships revealed an interconnected series of groups of #datasaveslives users in academia, health services and policy, and charities and patient networks. Thematic analysis of tweets showed that #datasaveslives was used for a broader range of purposes than indexing information, including event reporting, encouraging participation and action, and showing personal support for data sharing. CONCLUSIONS This study shows that a hashtag-based social media campaign was effective in encouraging a wide audience of stakeholders to disseminate positive examples of health research. Furthermore, the findings suggest the campaign supported community-building and bridging practices within and between the interdisciplinary sectors related to the field of health data science and encouraged individuals to demonstrate personal support for sharing health data. CLINICALTRIAL

Download Full-text

Use of Social Media in the Assessment of Relative Effectiveness: Explorative Review With Examples From Oncology (Preprint)

10.2196/preprints.7952 ◽

2017 ◽

Author(s):

Rachel R.J. Kalf ◽

Amr Makady ◽

Renske M.T. ten Ham ◽

Kim Meijboom ◽

Wim G. Goettsch ◽

...

Keyword(s):

Quality Of Life ◽

Social Media ◽

Adverse Events ◽

Real World ◽

Relative Effectiveness ◽

Health Data ◽

Real World Data ◽

World Data ◽

Effectiveness Assessment

BACKGROUND An element of health technology assessment constitutes assessing the clinical effectiveness of drugs, generally called relative effectiveness assessment. Little real-world evidence is available directly after market access, therefore randomized controlled trials are used to obtain information for relative effectiveness assessment. However, there is growing interest in using real-world data for relative effectiveness assessment. Social media may provide a source of real-world data. OBJECTIVE We assessed the extent to which social media-generated health data has provided insights for relative effectiveness assessment. METHODS An explorative literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to identify examples in oncology where health data were collected using social media. Scientific and grey literature published between January 2010 and June 2016 was identified by four reviewers, who independently screened studies for eligibility and extracted data. A descriptive qualitative analysis was performed. RESULTS Of 1032 articles identified, eight were included: four articles identified adverse events in response to cancer treatment, three articles disseminated quality of life surveys, and one study assessed the occurrence of disease-specific symptoms. Several strengths of social media-generated health data were highlighted in the articles, such as efficient collection of patient experiences and recruiting patients with rare diseases. Conversely, limitations included validation of authenticity and presence of information and selection bias. CONCLUSIONS Social media may provide a potential source of real-world data for relative effectiveness assessment, particularly on aspects such as adverse events, symptom occurrence, quality of life, and adherence behavior. This potential has not yet been fully realized and the degree of usefulness for relative effectiveness assessment should be further explored.

Download Full-text

Sentimental Analysis of Twitter Health Data using Machine Learning Techniques

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b6460.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 3458-3462

Keyword(s):

Machine Learning ◽

Social Media ◽

Health Data ◽

Machine Learning Techniques ◽

Related Data ◽

Interesting Study ◽

Learning Techniques ◽

Viable Solution ◽

Two Stages ◽

F Measure

With the huge development of Internet, more users have occupied with wellbeing networks, for example, medicinal discussions to assemble wellbeing related data, to share encounters about medications, treatments, analysis or to associate with different clients with comparable condition in social media. A lot of lookup has focused on examining Twitter health tweets for subject matter modeling using quite a number clustering approaches, but few have mentioned it for sentiment analysis. The truth that such statistics carries potential information for revealing the opinion of humans about fitness services and behaviors make it an interesting study. In these paper, universal sentiments about Twitter health data was investigated. Twitter, measuring and monitoring the occurrence of social health problems. The approach is based on two stages: In first stage separating perhaps applicable tweets utilizing a lot of uniquely made standard articulations, and afterward arranges these underlying messages utilizing machine learning techniques. Using the Twitter search API and Twitter metadata geocoded content, social media tweets were selected to start filtering. Once Tweets are correctly identified, the classifier was applied to data in order to filter out the tweets. Classification results were improved by detecting the values of ROC and f-measure. This report indicates that such a method provides a viable solution for quantifying and tracking the progression of health status within society

Download Full-text

Evaluation of a feasibility study using patient-generated health data from Twitter to identify, engage, and recruit cancer survivors in clinical trials in Los Angeles County (Preprint)

10.2196/preprints.29958 ◽

2021 ◽

Author(s):

Katja Reuter ◽

Praveen Angyan ◽

NamQuyen Le ◽

Thomas A. Buchanan

Keyword(s):

Clinical Trial ◽

Social Media ◽

Clinical Trials ◽

Los Angeles ◽

Cancer Survivors ◽

Los Angeles County ◽

Family Members ◽

Health Data ◽

The Social ◽

Twitter Users

BACKGROUND Failure to find and attract clinical trial participants remains a persistent barrier to clinical research. Researchers increasingly complement recruitment methods with social media-based methods. We hypothesized that user-generated data from cancer survivors and their family members/friends on the social network Twitter could be used to identify, engage, and recruit cancer survivors into cancer trials. OBJECTIVE This pilot examined the feasibility of using user-reported health data from cancer survivors and family members/friends on Twitter in Los Angeles County for enhancing clinical trial recruitment. We focused on six cancer conditions (breast, colon, kidney, lymphoma, lung cancer, and prostate). METHODS The social media intervention involved (1) monitoring cancer-specific posts about the six cancers by Twitter users in Los Angeles (L.A.) County to identify cancer survivors and their family members/friends, and (2) contacting eligible Twitter users with information about open cancer trials at the USC Norris Comprehensive Cancer Center (USC Norris). We reviewed both retrospective and prospective data published by Twitter users in L.A. County between July 28, 2017 and November 29, 2018. The study enrolled 124 open clinical trials at USC Norris. We used descriptive statistics to report the proportion of Twitter users who were identified, engaged, and enrolled. RESULTS We analyzed 107,424 Twitter posts in English by 25,032 unique Twitter users in L.A. County for the six cancer conditions. We identified and contacted 434 (1.7%) eligible cancer survivors (29.3 %; 127/434) and their family members/friends (70.3%; 305/434). Half of them were female and about a third was male. About one-fifth were Persons of Color, while most of them were White. About one-fifth (19.6%, 85/434) engaged with the outreach messages (cancer survivors: 38.2%, 33/85; family members/friends: 61.2%, 52/85). A quarter of those who engaged with the message were male, the majority were women, and about one-fifth were People of Color, while the majority was White. Nearly 12% (10/85) of the contacted users requested more information and 40% (4/10) set up a pre-screening. Two eligible candidates were transferred to USC Norris for further screening. Both were eligible for trial participation, but none of them enrolled. CONCLUSIONS Our findings demonstrate the potential of identifying and engaging cancer survivors and their family members/friends on Twitter. The optimization of downstream recruitment efforts such as screening for ‘digital populations’ on social media may be required. Future research could test the feasibility of the approach for other diseases, locations, languages, social media platforms, and types of research involvement (eg, survey research). Computer science methods could help to scale up the analysis of larger datasets to support more rigorous testing of the intervention. CLINICALTRIAL not applicable

Download Full-text