Big data from online debates to urban design and planning actions: Visualizing large-scale human-centric data for post-participation

Cities are dynamic entities, continuously evolving and shaped by their inhabitants. With the rise of digital technologies, urban practitioners increasingly rely on human-centered data collected through digital participation. These platforms gather public opinions in natural language, generating large-scale textual datasets about cities. However, the integration of this data into decision-making remains underexplored. This research introduces the concept of post-participation , referring to the phase following citizen engagement where data is processed, analyzed, and interpreted to inform urban decisions. Focusing on large-scale datasets from Hamburg, Germany, this study employs advanced AI-based methods, such as Natural Language Processing, Topic Modeling, and sentiment analysis, to efficiently extract and analyze relevant information. In addition, it develops visualization systems that present information through an analytical framework, revealing thematic structures, hierarchical relationships, semantic similarities, and high-dimensional clustering. These systems spatially track temporal evolution and emotional resonance of public discourse, offering multi-layered narratives for comparative topological analysis, temporal dynamics, and hierarchical structures. By addressing textual data visualization challenges, this paper balances clarity and complexity in visualization systems, integrating both quantitative and qualitative metrics. Ultimately, situated at the intersection of human–computer interaction, data analytics, and urbanism, this research aims to foster informed, transparent, and democratic design and planning processes.