Bikeshare system operators have leveraged online platforms to gather user feedback on station experiences and service quality. This crowdsourced data presents a valuable opportunity to enhance bikeshare planning and operations. However, planners have limited methods to analyze those qualitative data given the sparse nature of this data, which is insufficient for training comprehensive machine learning models. Addressing this challenge, this study employs a novel approach combining spatial analysis and Factor Analysis of Mixed Data (FAMD) to delve into bikeshare users’ perceptions and expectations. Focusing on Chicago’s bikeshare system, authors utilize its limited online comments to demonstrate the robustness of our algorithm and its applicability to both large and small datasets. The findings reveal a geographic pattern in feedback: negative comments on bike rebalancing, station locations, and facilities are concentrated in the city center, while dissatisfaction with the cycling environment is consistent across both urban and peripheral areas. Moreover, the demographic and employment characteristics of areas surrounding bikeshare stations significantly influence positive feedback, overshadowing the impact of station design and local infrastructure. Overall, this study offers a quantitative framework for leveraging limited crowdsourced feedback effectively, providing strategic insights for refining bikeshare planning and operational decisions.
