A Literature Review of Social Media-Based Data Mining for Health Outcomes Research

Ru, Boshu; Yao, Lixia

doi:10.1007/978-3-030-14714-3_1

Cited by 10 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although many of the findings were consistent with a different social media analysis on SIDS and safe sleep [ 24 ], an analysis of another social media format may have resulted in contradictory findings. Additionally, social media language can be difficult to analyze; there are often typos, informal writing, or abbreviations that can make the analysis challenging [ 38 ]. Although measures were taken to prevent misinterpretation and the research team refrained from interpretation as much as possible, it is possible that some of the original content may have been misunderstood or misinterpreted.…”

Section: Discussionmentioning

confidence: 99%

Sudden Infant Death Syndrome on Facebook: Qualitative Descriptive Content Analysis to Guide Prevention Efforts

Pretorius¹,

Choi²,

Kang³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

Background Sudden unexpected infant death (SUID), which includes the diagnosis of sudden infant death syndrome (SIDS), is a leading cause of infant mortality in the United States. Despite prevention efforts, many parents continue to create unsafe infant sleep environments and use potentially dangerous infant sleep and monitoring devices, ultimately leading to sleep-related infant deaths. Analyzing Facebook conversations regarding SIDS may offer a unique maternal perspective to guide future research and prevention efforts. Objective This study aims to describe and analyze conversations among mothers engaged in discussions about SIDS on a Facebook mother’s group. We were interested in understanding maternal knowledge of SIDS, identifying information sources for SIDS, describing actual infant sleep practices, exploring opinions regarding infant sleep products and monitoring devices, and discovering evidence of provider communication regarding SIDS. Methods We extracted and analyzed 20 posts and 912 comments from 512 mothers who participated in a specific Facebook mother’s group and engaged in conversations about SIDS. There were 2 reviewers who coded the data using qualitative descriptive content analysis. Themes were induced after discussion among researchers and after the study objectives were addressed. Results The theme of social support emerged, specifically informational and emotional support. A variety of informational sources for SIDS and safe sleep were identified, as was a continuum of infant sleep practices (ranging from unsafe to safe sleep per the American Academy of Pediatrics standards). There was widespread discussion regarding infant sleep products and monitoring devices. Embedded within conversations were (1) confusion among commonly used medical terminology, (2) the practice of unsafe infant sleep, (3) inconsistency in provider communication about SIDS, and (4) maternal anxiety regarding SIDS. Conclusions We uncovered new findings in this analysis, such as the commonality of infant sleep products and monitoring devices and widespread maternal anxiety regarding SIDS. Additionally, mothers who participated in the Facebook group provided and received informational and emotional support regarding SIDS via this social media format. Such results can guide future prevention efforts by informing health communication regarding SUID and safe sleep. Future provider and public health agency communication on the topic of SUID and safe sleep should be simple and clear, address infant sleep products and monitoring devices, address maternal anxiety regarding SIDS, and address the common practice of unsafe sleep.

show abstract

Section: Discussionmentioning

confidence: 99%

Sudden Infant Death Syndrome on Facebook: Qualitative Descriptive Content Analysis to Guide Prevention Efforts

Pretorius¹,

Choi²,

Kang³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Searching across disciplines, especially in an area where the terminology varies and evolves rapidly means that it is difficult to use tightly defined search terms. Many relevant keywords relating to SM have yet to be indexed into the MeSH system so it was not possible to rely purely on MeSH terms for searching [ 7 , 21 ]. Scoping review methods do not require a formal critical appraisal of the literature [ 19 ].…”

Section: Methodsmentioning

confidence: 99%

“…As the numbers of individuals using the internet for health-related purposes continues to rise, there has been a corresponding increased interest in exploring this online user generated content as a data source for health research [ 7 ]. The potential benefits of social media as a research resource for healthcare include reducing research costs [ 8 ], improving patient empowerment [ 9 ], engagement [ 10 ] and health communication [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Spontaneously generated online patient experience data - how and why is it being used in health research: an umbrella scoping review

Walsh

Dwumfour

Cave

et al. 2022

BMC Med Res Methodol

View full text Add to dashboard Cite

Purpose Social media has led to fundamental changes in the way that people look for and share health related information. There is increasing interest in using this spontaneously generated patient experience data as a data source for health research. The aim was to summarise the state of the art regarding how and why SGOPE data has been used in health research. We determined the sites and platforms used as data sources, the purposes of the studies, the tools and methods being used, and any identified research gaps. Methods A scoping umbrella review was conducted looking at review papers from 2015 to Jan 2021 that studied the use of SGOPE data for health research. Using keyword searches we identified 1759 papers from which we included 58 relevant studies in our review. Results Data was used from many individual general or health specific platforms, although Twitter was the most widely used data source. The most frequent purposes were surveillance based, tracking infectious disease, adverse event identification and mental health triaging. Despite the developments in machine learning the reviews included lots of small qualitative studies. Most NLP used supervised methods for sentiment analysis and classification. Very early days, methods need development. Methods not being explained. Disciplinary differences - accuracy tweaks vs application. There is little evidence of any work that either compares the results in both methods on the same data set or brings the ideas together. Conclusion Tools, methods, and techniques are still at an early stage of development, but strong consensus exists that this data source will become very important to patient centred health research.

show abstract

“…Electronic health records seem to raise more concern in medical informatics in the analysis of patients' health information or treatment effectiveness (see, for example, Strekalova, 2017). However, a large volume of patient-generated health-outcomes data has been created or recorded by patients or medical groups in social networks or media, which is contributed voluntarily and not limited to a single geographical location or specific groups (Ru and Yao, 2019). This patient-generated health-outcomes data, containing rich information, provides a valuable data source for health-related information behavior research.…”

Section: Research On the Practice Of Health Informationmentioning

confidence: 99%

Exploring the topic structure and evolution of associations in information behavior research through co-word analysis

Deng

Xia²,

et al. 2020

Journal of Librarianship and Information Science

View full text Add to dashboard Cite

This study aims to reveal the distribution of topics, and the associations among them, in information behavior research from 2009 to 2018. Working with a collection of 6744 publications from the Web of Science database, co-word analysis is used to investigate the overall topic structure, the associations among the topics, and their evolution in different years, which is supplemented by visualization with science maps. The results uncovered an unbalanced distribution of topics, and that the topics cluster into six communities representing subdivisions of this field: information behavior in patient-centered studies; information interaction in the digital environment; information literacy in health and academic contexts; health literacy on the Internet; information behavior in child-centered studies; and information behavior in medical informatics. The findings supplement and provide refinements to work on the state of this field, and help researchers obtain an overview of the past decade to guide their future work.

show abstract

A Literature Review of Social Media-Based Data Mining for Health Outcomes Research

Cited by 10 publications

References 29 publications

Sudden Infant Death Syndrome on Facebook: Qualitative Descriptive Content Analysis to Guide Prevention Efforts

Sudden Infant Death Syndrome on Facebook: Qualitative Descriptive Content Analysis to Guide Prevention Efforts

Spontaneously generated online patient experience data - how and why is it being used in health research: an umbrella scoping review

Exploring the topic structure and evolution of associations in information behavior research through co-word analysis

Contact Info

Product

Resources

About