Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward Equitable Access: Leveraging Crowdsourced Reviews to Investigate Public Perceptions of Health Resource Accessibility

Zhaoqian Xue, Guanhong Liu, Chong Zhang, Kai Wei, Qingcheng Zeng, Songhua Hu, Wenyue Hua, Lizhou Fan, Yongfeng Zhang, Lingyao Li

TL;DR

The paper develops a scalable framework that uses crowdsourced Google Maps reviews and DeBERTa-based NLP to create a high-resolution index of public perception of health-resource accessibility in the United States. It links these perception scores to county-level socioeconomic and demographic factors via Partial Least Squares regression and validates the approach against national survey data. Results show pronounced spatial-temporal disparities, peak amplification during COVID-19, and persistent, uneven recovery shaped by race, insurance status, income, and education. The work demonstrates the utility of crowdsourced data for real-time health equity monitoring and offers policy-relevant insights for building a more resilient healthcare system.

Abstract

Monitoring health resource disparities during public health crises is critical, yet traditional methods, like surveys, lack the requisite speed and spatial granularity. This study introduces a novel framework that leverages: 1) crowdsourced Google Maps reviews (2018-2021) and 2) advanced NLP (DeBERTa) to create a high-resolution, spatial-temporal index of public perception of health resource accessibility in the United States. We then employ Partial Least Squares (PLS) regression to link this perception index to a range of socioeconomic and demographic drivers. Our results quantify significant spatial-temporal shifts in perceived access, confirming that disparities peaked during the COVID-19 crisis and only partially recovered post-peak. We identify political affiliation, racial composition, and educational attainment as primary determinants of these perceptions. This study validates a scalable method for real-time health equity monitoring and provides actionable evidence for interventions to build a more resilient healthcare infrastructure.

Toward Equitable Access: Leveraging Crowdsourced Reviews to Investigate Public Perceptions of Health Resource Accessibility

TL;DR

The paper develops a scalable framework that uses crowdsourced Google Maps reviews and DeBERTa-based NLP to create a high-resolution index of public perception of health-resource accessibility in the United States. It links these perception scores to county-level socioeconomic and demographic factors via Partial Least Squares regression and validates the approach against national survey data. Results show pronounced spatial-temporal disparities, peak amplification during COVID-19, and persistent, uneven recovery shaped by race, insurance status, income, and education. The work demonstrates the utility of crowdsourced data for real-time health equity monitoring and offers policy-relevant insights for building a more resilient healthcare system.

Abstract

Monitoring health resource disparities during public health crises is critical, yet traditional methods, like surveys, lack the requisite speed and spatial granularity. This study introduces a novel framework that leverages: 1) crowdsourced Google Maps reviews (2018-2021) and 2) advanced NLP (DeBERTa) to create a high-resolution, spatial-temporal index of public perception of health resource accessibility in the United States. We then employ Partial Least Squares (PLS) regression to link this perception index to a range of socioeconomic and demographic drivers. Our results quantify significant spatial-temporal shifts in perceived access, confirming that disparities peaked during the COVID-19 crisis and only partially recovered post-peak. We identify political affiliation, racial composition, and educational attainment as primary determinants of these perceptions. This study validates a scalable method for real-time health equity monitoring and provides actionable evidence for interventions to build a more resilient healthcare infrastructure.

Paper Structure

This paper contains 16 sections, 5 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset and Methodology
  4. Data Collection
  5. Keywords ontology and development
  6. Text classification
  7. Partial Least Squares (PLS) Regression
  8. Results
  9. RQ1: Do health resource disparities, as perceived by the public, exist across different regions in the United States?
  10. RQ2: Are these perceived health resource disparities correlated with the socioeconomic and demographic factors?
  11. RQ3: Did the COVID-19 pandemic exacerbate health resource accessibility as perceived by the public?
  12. Discussion
  13. Principal Findings and Implications
  14. Limitations and Data Representativeness
  15. Future Research Directions
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Classification performance of candidate models: (a) Precision, (b) Recall, (c) F1-score, and (d) Training and testing accuracy.
  • Figure 2: Comparison between weighted delayed ratio reported by US Census Bureau and average perception scores by online reviews.
  • Figure 3: Health resource availability trends across pandemic periods.
  • Figure 4: Geographic patterns of the perceived health resource disparities across the United States.
  • Figure 5: Moran's I scatterplots across pandemic periods.