[Paper Review] An Interactive Data Visualization and Analytics Tool to Evaluate Mobility and Sociability Trends During COVID-19

Fan Zuo, Jingxing Wang+6 more|arXiv (Cornell University)|Jun 26, 2020

Traffic Prediction and Management Techniques9 references33 citations

TL;DR

The paper describes a cloud-based interactive dashboard that fuses multi-source mobility and sociability data to analyze COVID-19 impacts in NYC and Seattle, with an architecture supporting real-time analytics and visualization.

ABSTRACT

The COVID-19 outbreak has dramatically changed travel behavior in affected cities. The C2SMART research team has been investigating the impact of COVID-19 on mobility and sociability. New York City (NYC) and Seattle, two of the cities most affected by COVID-19 in the U.S. were included in our initial study. An all-in-one dashboard with data mining and cloud computing capabilities was developed for interactive data analytics and visualization to facilitate the understanding of the impact of the outbreak and corresponding policies such as social distancing on transportation systems. This platform is updated regularly and continues to evolve with the addition of new data, impact metrics, and visualizations to assist public and decision-makers to make informed decisions. This paper presents the architecture of the COVID related mobility data dashboard and preliminary mobility and sociability metrics for NYC and Seattle.

Motivation & Objective

• Motivate the need to understand how COVID-19 policies affect transportation and social behavior.
• Develop an all-in-one, scalable dashboard that ingests diverse data sources for mobility and sociability analysis.
• Provide real-time analytics and visualizations to support public decision-makers in evaluating outbreak impacts.

Proposed method

• Cloud-based data ingestion pipeline with data accuracy, timeliness, validity, and granularity checks.
• Integrated data warehouse for storing fused mobility and sociability data from multiple sources.
• Two main dashboard boards: mobility board (traffic volume, travel times, ridership, crashes, etc.) and sociability board (crowd density, social distancing from cameras).
• Real-time analytics and visualizations with scenario analysis and spatiotemporal aggregations.
• Connection to MATSim for agent-based simulation of network performance and emissions.

Experimental results

Research questions

• RQ1 How did mobility patterns (traffic volume, travel time, transit ridership) change in NYC and Seattle during COVID-19 stay-at-home orders?
• RQ2 How did sociability indicators (crowd density, social distancing compliance) evolve, and what is their relationship to policy measures?
• RQ3 Can the dashboard support scenario analysis and provide timely insights for reopening decisions?
• RQ4 What is the role of multi-source data fusion in measuring mobility and sociability during a pandemic?
• RQ5 How can the platform be extended to additional cities and data sources?

Key findings

• Mobility metrics show declines in traffic and transit usage with varying recovery patterns across NYC and Seattle.
• Travel time patterns flattened during stay-at-home orders, with partial recoveries observed later, and reliability improvements noted in Seattle.
• Sociability metrics indicate changes in crowd density and social distancing compliance, derived from video processing of real-time cameras.
• The platform demonstrates low-latency, cloud-based data processing capable of real-time analytics and visualization across multiple data sources.
• Analyses suggest a potential shift in mode choice with continued low transit usage while auto traffic begins to rise.
• The dashboard is designed to be scalable to additional cities and data sources.