Social Media Image Analysis for Public Health

Garimella, Venkata Rama Kiran; Alfayad, Abdulrahman; Weber, Ingmar

doi:10.1145/2858036.2858234

Cited by 71 publications

(44 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A linguistic analysis [15] of Twitter activity found Twitter-derived statistics can improve predictive accuracy for some health-related statistics at county level. User-provided and machine-generated geo-tags of images from Instagram can also be used to infer a county's health statistics, such as obesity statistics [22]. Paul & Dredze [48] applied a topic model to health-related tweets and discovered quantitative correlations with public health data.…”

Section: Social Media and Public Healthmentioning

confidence: 99%

Managing Uncertainty

Gui

Kou

Pine

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Recently, diseases like H1N1 influenza, Ebola, and Zika virus have created severe crises, requiring public resources and personal behavior adaptation. Crisis Informatics literature examines interconnections of people, organizations, and IT during crisis events. However, how people use technology to cope with disease crises (outbreaks, epidemics, and pandemics) remains understudied. We investigate how individuals used social media in response to the outbreak of Zika, focusing on travel-related decisions. We found that extreme uncertainty and ambiguity characterized the Zika virus crisis. To cope, people turned to social media for information gathering and social learning geared towards personal risk assessment and modifying decisions when dealing with partial and conflicting information about Zika. In particular, individuals sought local information and used socially informed logical reasoning to deduce the risk at a specific locale. We conclude with implications for designing information systems to support individual risk assessment and decision-making when faced with uncertainty and ambiguity during public health crises.

show abstract

Section: Social Media and Public Healthmentioning

confidence: 99%

Managing Uncertainty

Gui

Kou

Pine

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…The only previous work we are aware of that used automatically extracted image tags is [21], which found that image tags were predictive of lifestyle factors; for example, "glass", "liquid" and "beverage" were associated with excessive drinking. The authors suggested that image tags may be useful for identifying stigmatizing behaviors, where social media users may post images of an activity but not tag the activity in an explicit way.…”

Section: Discussionmentioning

confidence: 99%

“…A few studies have looked at substance use on Instagram, including electronic cigarettes [18], marijuana [19], and opioids [20]. Garimella et al [21] looked more broadly at lifestyle choices in Instagram, including diet, physical activity, and drinking. Notably, this study used both text features and image features, which also we do in our study.…”

Section: Prior Workmentioning

confidence: 99%

#Healthy Selfies: Exploration of Health Topics on Instagram (Preprint)

Muralidhara¹,

Paul²

2018

Preprint

View full text Add to dashboard Cite

Background: Social media provides a complementary source of information for public health surveillance. The dominate data source for this type of surveillance is the microblogging platform Twitter, which is convenient due to the free availability of public data. Less is known about the utility of other social media platforms, despite their popularity. Objective: This work aims to characterize the health topics that are prominently discussed in the image-sharing platform Instagram, as a step toward understanding how this data might be used for public health research. Methods: The study uses a topic modeling approach to discover topics in a dataset of 96,443 Instagram posts containing hashtags related to health. We use a polylingual topic model, originally developed for datasets in different natural languages, to model different modalities of data: hashtags, caption words, and image tags automatically extracted using a computer vision tool. Results: We identified 47 health-related topics in the data, covering ten broad categories: acute illness, alternative medicine, chronic illness and pain, diet, exercise, healthcare & medicine, mental health, musculoskeletal health and dermatology, sleep, and substance use. The most prevalent topics were related to diet and exercise. Conclusions: A large and diverse set of health topics are discussed in Instagram. The extracted image tags were generally too coarse and noisy to be used for identifying posts, but were in some cases accurate for identifying images relevant to studying diet and substance use. Instagram shows potential as a source of public health information, though limitations in data collection and metadata availability may limit its use in comparison to platforms like Twitter.

show abstract

“…For instance, Wagner et al [54] analyzed data from an online recipe platform to understand the association between geographic proximity and shared dietary preferences and the extent to which temporal information helps to predict these preferences. Twitter and Facebook posts [1] as well as the content of Instagram images [23] have further been found to correlate with CDC reported prevalence of obesity in different geographical regions, as well as in helping infer caloric and nutrient consumption. Weber and Mejova [58], recently showed the feasibility of using crowd-sourcing to infer body weight categories from profile pictures shared on Twitter.…”

Section: Related Workmentioning

confidence: 99%

Computational Approaches Toward Integrating Quantified Self Sensing and Social Media

Choudhury

Kumar

Weber

2017

Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing

Self Cite

View full text Add to dashboard Cite

The growing amount of data collected by quantified self tools and social media hold great potential for applications in personalized medicine. Whereas the first includes health-related physiological signals, the latter provides insights into a user’s behavior. However, the two sources of data have largely been studied in isolation. We analyze public data from users who have chosen to connect their MyFitnessPal and Twitter accounts. We show that a user’s diet compliance success, measured via their self-logged food diaries, can be predicted using features derived from social media: linguistic, activity, and social capital. We find that users with more positive affect and a larger social network are more successful in succeeding in their dietary goals. Using a Granger causality methodology, we also show that social media can help predict daily changes in diet compliance success or failure with an accuracy of 77%, that improves over baseline techniques by 17%. We discuss the implications of our work in the design of improved health interventions for behavior change.

show abstract

Social Media Image Analysis for Public Health

Cited by 71 publications

References 23 publications

Managing Uncertainty

Managing Uncertainty

#Healthy Selfies: Exploration of Health Topics on Instagram (Preprint)

Computational Approaches Toward Integrating Quantified Self Sensing and Social Media

Contact Info

Product

Resources

About