Factors influencing crowdsourcing riders' satisfaction based on online comments on real-time logistics platform

Real-time logistics (RTL), which is mainly organized by crowdsourcing, has grown rapidly in recent years. Crowdsourcing riders are the main undertakers of RTL. This paper uses crowdsourcing riders' online comments as data sources, and uses text mining techniques such as sentiment analysis and Latent Dirichlet Allocation (LDA) topic modeling to analyze the factors that bring satisfaction and dissatisfaction to riders. The research results show that in addition to basic income, riders expect the platform to provide them with better services, skills training and safety insurance before work can bring satisfaction to riders. The lack of timely information feedback on the current platform and inaccurate order matching are the reasons for the dissatisfaction of riders. Research also shows that riders can easily gain a sense of accomplishment to help others in the process of completing RTL distribution. Interactions with merchants and customers will also affect riders' satisfaction.