Social Media Image Analysis for Public Health

Venkata Rama Kiran Garimella, Abdulrahman Alfayad, Ingmar Weber

2016 · 93 citations · 23 references

Concepts

TL;DR

Social media data, including Instagram images, have been used to track public health trends such as influenza and obesity, and images of social gatherings may reveal lifestyle disease information not captured in text posts. This study investigates whether geo‑tagged Instagram images and their associated tags can serve as a viable data source for public health surveillance. The authors evaluate the usefulness of user‑provided tags and machine‑generated image annotations for inferring county‑level health statistics. Both tag types can predict county health metrics, with user tags generally outperforming machine tags except for excessive drinking, where machine tags such as “liquid” and “glass” yield better models, indicating promise for studying substance abuse.

Abstract

Several projects have shown the feasibility to use emph{textual} social media data to track public health concerns, such as temporal influenza patterns or geographical obesity patterns. In this paper, we look at whether geo-tagged emph{images} from Instagram also provide a viable data source. Especially for "lifestyle" diseases, such as obesity, drinking or smoking, images of social gatherings could provide information that is not necessarily shared in, say, tweets. In this study, we explore whether (i) tags provided by the users and (ii) annotations obtained via automatic image tagging are indeed valuable for studying public health. We find that both user-provided and machine-generated tags provide information that can be used to infer a county's health statistics. Whereas for most statistics user-provided tags are better features, for predicting excessive drinking machine-generated tags such as "liquid' and "glass' yield better models. This hints at the potential of using machine-generated tags to study substance abuse.

References

23