Integrating crowdsourced data in the built environment studies: A systematic review.

The integration of crowdsourced data has become central to contemporary built environment studies, driven by the rapid growth in digital technologies and participatory approaches that characterize modern urbanism. Despite its potential, a systematic framework for its analysis remains underdeveloped. This review, conducted in accordance with the PRISMA protocol, examines the use of crowdsourced data in shaping the built environment, scrutinizing its applications, crowdsourcing techniques, methodologies, and comparison with other big data forms. From 226 relevant studies, this study uncovers the evolving thematic landscape of crowdsourced data through a longitudinal analysis (2013-2024), revealing the driving forces that have shifted its representation over time. Additionally, by examining the cultural dimensions and contextual variability, this study demonstrates how identical data is interpreted in markedly different ways across diverse geographic and social contexts. These findings underscore the inmportance of adopting context-sensitive and culturally aware approaches to effectively leverage crowdsourced data in the built environment research. The novelty of this review lies in reframing crowdsourced data not merely as an application tool but as a lens for understanding broader cultural and technological shifts, offering both theoretical and practical insights into its role in the built environment. By advancing our understanding of the unique contributions of crowdsourced data and its complementary role to other big data types, this review provides actionable recommendations for urban planners and policymakers. Ultimately, these findings promote more inclusive and sustainable urban development, fostering cities that better respond to the needs of diverse populations.
Competing Interests: Declaration of competing interest The authors, Qiuyi Yang, Bo Zhang, Jiawen Chen, Yang Song and Xiwei Shen (corresponding authors), on behalf of all contributors to this manuscript, declare that there are no financial or personal relationships with other individuals or organizations that could inappropriately influence or bias the content of this paper. None of the authors have any competing interests to disclose in relation to employment, consultancies, stock ownership, honoraria, paid expert testimony, patent applications/registrations, grants, or other funding. Each author has confirmed that they have no conflicts of interest to declare and that the information provided in this statement is accurate and complete.
(Copyright © 2024 Elsevier Ltd. All rights reserved.)