Social Media Analytics for Environmental Health

Social Media Analytics for Environmental Health

Spatial Health Lab

Image
A hand holding a smartphone with social media app icons.

Environmental exposures and health issues can change quickly, often within overlooked populations. Thousands of Americans are using social media every day to describe environmental exposures and health issues they have experienced. By analyzing public social media posts, we can listen to underserved voices and quickly identify new environmental health issues and concerns.

Social media also presents unique opportunities and challenges for environmental health communications. Environmental health posts can quickly gain attention and become ‘viral’, where millions of social media users view a post in a short period of time. Public health agencies can use virality to raise awareness about urgent environmental health issues. Unfortunately, health misinformation can also spread quickly on social media, and the spread of misinformation can be hard to stop once it’s become viral.

Image
Visualization of data points representing conversations in a community.

Specific research projects

Image
""

The Oregon State University Center for Advancing Science, Practice, Programming and Policy in Research Translation for Children’s Environmental Center (ASPIRE Center).

NIEHS P2C (P2C ES033432-01)

Development Core, Co-PIs: Hystad & MacDonald

ASPIRE is one of six centers in the United States funded by the National Institute of Environmental Health Sciences (NIEHS) to develop strategies to translate key children’s environmental health research findings to relevant stakeholders. Working together, the Spatial Health Lab and ASPIRE downloaded more than 650 million social media posts and are developing best practices for analyzing social media relevant to children’s environmental health. The primary goals of this interdisciplinary project are to identify children’s environmental health concerns for communities across the United States and develop methods for identifying and disrupting children’s environmental health misinformation.

Research paper highlights

 

Larkin, A., & Hystad, P. (2020). Integrating Geospatial Data and Social Media in Bidirectional Long-Short Term Memory Models to Capture Human Nature Interactions. Comput. J., 65, 667-678. DOI: 10.1093/comjnl/bxaa094

 

 

Larkin, A. (2019). Developing climate change communication strategies with game theory. Net Journal of Social Sciences. DOI: 10.30918/NJSS.71.19.012

 

GitHub repositories

ChildrensHealthSocialMediaASP3IRE

This github repository contains python scripts and custom classes for ingesting social media records into a Neo4j database as well as deep learning models and jupyter notebooks for and researching attitudes, perceptions, behaviors, and children's environmental health social media misinformation.

GreenTweet_MultivariateBiLSTM

The purpose of this project is to download text from twitter posts related to urban nature, or "greenspace", preprocess the text for developing classifiers, create a multivariate classifier for greenspace related pathways of action, and evaluate model performance.

Game-Theory-Climate-Change-Communication

Support for climate change regulation significantly differs between the scientific community and general public in the US. Previous studies suggest partisan politics together with increasingly partisan news media coverage is partly responsible for the divergence between public and scientific opinion. This project utililzes game theory models to identify best strategies for scientists to use when engaging media to maximmize impact on climate change communication.