Using crowdsourced data to assess safety in developing countries: the case study of Eastern Cairo, Egypt

Crowdsourced data refers to data that is collected and shared by a large number of individuals or organizations, often through the use of digital technologies such as mobile devices and social media. The shortage in crash data collection in developing countries makes it difficult to fully understand and address road safety issues in these regions. In developing countries, crowdsourced data can be a valuable tool for collecting crash data and improving road safety, particularly in urban areas where the majority of road crashes occur. This study is the first to develop safety performance functions using crowdsourced data by adopting a Negative Binomial structure model and Full Bayes (FB) model to investigate traffic safety for urban road networks and provide insights into the impact of roadway characteristics. Furthermore, as a part of the safety management process, network screening has been undergone through applying two different methods to rank the most hazardous road segments: Potential Collision Reduction (PCR) method (adopted in the Highway Safety Manual (HSM)) as well as a graphical method using GIS tools to compare and validate. The analysis revealed that segment length, number of lanes, and pedestrian density were significant factors positively associated with crash frequency. FB models with spatial correlation showed better performance in terms of logic and model fit compared to traditional models. The analysis found that both PCR and GIS-based kriging methods effectively identified hazardous segments, with kriging using summation criteria providing more consistent results when validated against PCR outcomes. Recommendations were proposed to improve pedestrian behavior, and control access points and U-turns, based on the observed impact on safety. Lastly, recommendations were suggested for policymakers to ensure safer roads and limitations regarding data coverage and the need for complementary official crash data were highlighted to guide future research.