Evaluating the Coverage and Spatiotemporal Accuracy of Crowdsourced Reports Over Time: A Case Study of Waze Event Reports in Tennessee

Abstract

Researchers are increasingly aware of the importance of crowdsourced data and consider them as possible complementary data sources to existing traffic monitoring systems. In this study, we investigated the coverage, timeliness, and location accuracy of Waze user reports over the years (2018–2021) by comparing their reports with official abnormal event records. The results indicate that the coverage of Waze reports is not constant over time and space. The matching rate of Waze crashes to official records was affected by traffic volumes. It dropped at the start of the COVID-19 pandemic (March 2020) and recovered gradually in 2021, coinciding with the decline and recovery of traffic during the COVID-19 period. Other factors affecting the matching rate include incident duration and location. In addition, Waze reports were timely. On average, 55% of the crashes were reported sooner by Waze users than by the official records. Location accuracy was evaluated as well, and the average absolute distance difference was 0.40 mi for crashes and 0.29 mi for stopped vehicles. Nearly all (90%) of the distance differences between Waze reports and Tennessee Department of Transportation (TDOT) records were between −0.85 and 0.80 mi for crashes and −0.67 to 0.62 mi for stopped vehicles. No obvious change in the spatiotemporal accuracy over time could be observed. Moreover, those Waze reports that could not be matched to TDOT records were analyzed, and the number of crashes covered by those reports was estimated. The results suggest that Waze reports have potential value in identifying missed/unreported crash records and complementing the existing incident database.