Socio-spatial Self-organizing Maps: Using Social Media to Assess Relevant Geographies for Exposure to Social Processes

TL;DR

This paper introduces Socio-spatial Self-organizing Maps (SS-SOM), a novel method to identify regions based on social media attitudes, enabling better assessment of social environmental influences on health outcomes.

Contribution

The paper presents SS-SOM, a new neural network-based clustering method that captures social attitudes from Twitter data and improves regional exposure measurement over traditional administrative boundaries.

Findings

SS-SOM clusters are robust to missing data.

Exposure measures change by up to 42% compared to Zip code-based measures.

SS-SOM provides more relevant regional social attitude assessments.

Abstract

Social media offers a unique window into attitudes like racism and homophobia, exposure to which are important, hard to measure and understudied social determinants of health. However, individual geo-located observations from social media are noisy and geographically inconsistent. Existing areas by which exposures are measured, like Zip codes, average over irrelevant administratively-defined boundaries. Hence, in order to enable studies of online social environmental measures like attitudes on social media and their possible relationship to health outcomes, first there is a need for a method to define the collective, underlying degree of social media attitudes by region. To address this, we create the Socio-spatial-Self organizing map, "SS-SOM" pipeline to best identify regions by their latent social attitude from Twitter posts. SS-SOMs use neural embedding for text-classification, and augment traditional SOMs to generate a controlled number of non-overlapping, topologically-constrained and topically-similar clusters. We find that not only are SS-SOMs robust to missing data, the exposure of a cohort of men who are susceptible to multiple racism and homophobia-linked health outcomes, changes by up to 42% using SS-SOM measures as compared to using Zip code-based measures.