A call for an ethical framework when using social media data for artificial intelligence applications in public health research

Gilbert, Jean-Philippe; Ng, Victoria; Niu, Jingcheng; Rees, Erin E.

doi:10.14745/ccdr.v46i06a03

Cited by 14 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, there is a need to balance between the benefits of having large quantities of granular information for analysis and the need to ensure individuals cannot be (re)identified. This is particularly true with AI methods, given the large quantity of information that is usually required to train the model (( 54 , 57 , 62 , 63 )). In the case of digital data, which may be publicly available, but where permission to use for surveillance purposes has not been acquired, it is not clear how/whether informed consent can or needs to be obtained.…”

Section: Discussionmentioning

confidence: 99%

“…In the case of digital data, which may be publicly available, but where permission to use for surveillance purposes has not been acquired, it is not clear how/whether informed consent can or needs to be obtained. Particular care needs to be taken to ensure that data are anonymized and confidential information is not revealed (( 63 )). Protection of digital data and transparency in how and what data is acquired, stored, and used are key to maintaining public trust and ensuring the sustainability of these systems (( 57 , 64 )), and thus progress towards digital data governance is needed to fully operationalize these data sources.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Innovations in public health surveillance: An overview of novel use of data and analytic methods

Rilkoff,

Struck,

Ziegler

et al. 2024

CCDR

View full text Add to dashboard Cite

Innovative data sources and methods for public health surveillance (PHS) have evolved rapidly over the past 10 years, suggesting the need for a closer look at the scientific maturity, feasibility, and utility of use in real-world situations. This article provides an overview of recent innovations in PHS, including data from social media, internet search engines, the Internet of Things (IoT), wastewater surveillance, participatory surveillance, artificial intelligence (AI), and nowcasting. Examples identified suggest that novel data sources and analytic methods have the potential to strengthen PHS by improving disease estimates, promoting early warning for disease outbreaks, and generating additional and/or more timely information for public health action. For example, wastewater surveillance has re-emerged as a practical tool for early detection of the coronavirus disease 2019 (COVID-19) and other pathogens, and AI is increasingly used to process large amounts of digital data. Challenges to implementing novel methods include lack of scientific maturity, limited examples of implementation in real-world public health settings, privacy and security risks, and health equity implications. Improving data governance, developing clear policies for the use of AI technologies, and public health workforce development are important next steps towards advancing the use of innovation in PHS.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Innovations in public health surveillance: An overview of novel use of data and analytic methods

Rilkoff,

Struck,

Ziegler

et al. 2024

CCDR

View full text Add to dashboard Cite

show abstract

“…Given that the content often examined in psychological research is of a sensitive nature (eg, mental health issues and personal experiences), it may be particularly relevant to consider the ethical implications of using publicly available data (eg, social media), which might be linked to a person’s identity. We encourage researchers to consult ethics boards when determining whether approval is needed to use such data, even if it is publicly available [ 121 , 122 ]. Furthermore, social media data can be more prone to grammatical errors and increased ambiguity (eg, owing to spelling errors and slang) compared with scientific literature and formal documentation and may require more in-depth preprocessing depending on the nature of the research question.…”

Section: Discussionmentioning

confidence: 99%

Examining Analytic Practices in Latent Dirichlet Allocation Within Psychological Science: Scoping Review

Hagg¹,

Merkouris²,

O’Dea³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

Background Topic modeling approaches allow researchers to analyze and represent written texts. One of the commonly used approaches in psychology is latent Dirichlet allocation (LDA), which is used for rapidly synthesizing patterns of text within “big data,” but outputs can be sensitive to decisions made during the analytic pipeline and may not be suitable for certain scenarios such as short texts, and we highlight resources for alternative approaches. This review focuses on the complex analytical practices specific to LDA, which existing practical guides for training LDA models have not addressed. Objective This scoping review used key analytical steps (data selection, data preprocessing, and data analysis) as a framework to understand the methodological approaches being used in psychology research using LDA. Methods A total of 4 psychology and health databases were searched. Studies were included if they used LDA to analyze written words and focused on a psychological construct or issue. The data charting processes were constructed and employed based on common data selection, preprocessing, and data analysis steps. Results A total of 68 studies were included. These studies explored a range of research areas and mostly sourced their data from social media platforms. Although some studies reported on preprocessing and data analysis steps taken, most studies did not provide sufficient detail for reproducibility. Furthermore, the debate surrounding the necessity of certain preprocessing and data analysis steps is revealed. Conclusions Our findings highlight the growing use of LDA in psychological science. However, there is a need to improve analytical reporting standards and identify comprehensive and evidence-based best practice recommendations. To work toward this, we developed an LDA Preferred Reporting Checklist that will allow for consistent documentation of LDA analytic decisions and reproducible research outcomes.

show abstract

“…The use of wearable sensors raises several legal, ethical, and cultural issues associated with collecting, storing, and analysing these data. Issues include informed consent, privacy, anonymisation and balancing these issues with the benefits of using big data for the common good [60]. Digital technologies give users the option to control their data by allowing or revoking access to their data by opting in or out.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Assessing the Impact of a New Urban Greenway Using Mobile, Wearable Technology-Elicited Walk- and Bike-Along Interviews

2022

View full text Add to dashboard Cite

Physical inactivity is the fourth leading risk factor for global mortality, causing an estimated 3.3 million deaths worldwide. Characteristics of the built environment, including buildings, public spaces, pedestrian and cycling infrastructure, transportation networks, parks, trails and green spaces can facilitate or constrain physical activity. However, objective study of built environment interventions on physical activity remains challenging due to methodological limitations and research gaps. Existing methods such as direct observations or surveys are time and labour intensive, and only provide a static, cross-sectional view of physical activity at a specific point in time. The aim of this study was to develop a novel method for objectively and inexpensively assessing how built environment changes may influence physical activity. We used a novel, unobtrusive method to capture real-time, in situ data from a convenience sample of 25 adults along a newly constructed urban greenway in an area of high deprivation in Belfast, UK. Walk/bike-along interviews were conducted with participants using a body-worn or bicycle-mounted portable digital video camera (GoPro HERO 3+ camera) to record their self-determined journeys along the greenway. This is the first study to demonstrate the feasibility of using wearable sensors to capture participants’ responses to the built environment in real-time during their walking and cycling journeys. These findings contribute to our understanding of the impact of real-world environmental interventions on physical activity and the importance of precise, accurate and objective measurements of environments where the activity occurs.

show abstract

A call for an ethical framework when using social media data for artificial intelligence applications in public health research

Cited by 14 publications

References 26 publications

Innovations in public health surveillance: An overview of novel use of data and analytic methods

Innovations in public health surveillance: An overview of novel use of data and analytic methods

Examining Analytic Practices in Latent Dirichlet Allocation Within Psychological Science: Scoping Review

Assessing the Impact of a New Urban Greenway Using Mobile, Wearable Technology-Elicited Walk- and Bike-Along Interviews

Contact Info

Product

Resources

About