Discovering Latent Patterns of Urban Cultural Interactions in WeChat for Modern City Planning

Abstract: Cultural activity is an inherent aspect of urban life and the success of a modern city is largely determined by its capacity to offer generous cultural entertainment to its citizens. To this end, the optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as it can reduce financial costs in terms of planning and improve quality of life in the city, more generally. In this paper, we make use of a large longitudinal dataset of user location check-ins from the online social network WeChat to develop a data-driven framework for cultural planning in the city of Beijing. We exploit rich spatio-temporal representations on user activity at cultural venues and use a novel extended version of the traditional latent Dirichlet allocation model that incorporates temporal information to identify latent patterns of urban cultural interactions. Using the characteristic typologies of mobile user cultural activities emitted by the model, we determine the levels of demand for different types of cultural resources across urban areas. We then compare those with the corresponding levels of supply as driven by the presence and spatial reach of cultural venues in local areas to obtain high resolution maps that indicate urban regions with lack of cultural resources, and thus give suggestions for further urban cultural planning and investment optimisation.

• The paper introduces an extended TLDA model integrating time-stamped WeChat check-ins to detect six distinct urban cultural engagement patterns.
• The paper employs the POPTICS algorithm to cluster user activity and develops a Demand-Supply Ratio to identify imbalances in cultural resource distribution.
• The paper demonstrates that areas with high Demand-Supply Ratios correspond to longer travel distances, providing actionable insights for policy makers.

Discovering Latent Patterns of Urban Cultural Interactions in WeChat for Urban Planning

Introduction

The paper investigates the intersection of urban cultural planning and data analytics by leveraging WeChat check-ins to extract latent cultural interaction patterns in Beijing. It utilizes an extended version of latent Dirichlet allocation (LDA) to incorporate temporal information into cultural interaction analysis, aiming to optimize the distribution of cultural resources across the city. The implications are significant for both reducing planning costs and enhancing urban quality of life by identifying cultural under-served areas.

Methodology

Data Collection

The research exploits a comprehensive dataset derived from WeChat - a prevalent messaging app with extensive user engagement in China, particularly in Beijing. With millions of daily active users, the dataset offers a granular view of user movements and cultural venue interactions, tracked through time-stamped check-ins.

Extended LDA and Temporal Importance

A crucial enhancement introduced is the temporal latent Dirichlet allocation (TLDA) model, which modifies classical LDA to consider timing elements of user check-ins at cultural venues. This approach identifies six discernible latent patterns from user data, reflecting diverse cultural engagement habits across different times of the day and week. Evaluation of this model considers a novel metric, Temporal Coherence Value (TCV), to ensure high temporal resolution in pattern discernment.

Cultural Demand-Supply Analysis

POPTICS Algorithm

The study employs POPTICS, a personalized adaptation of traditional clustering methods, to delineate user activity clusters and map these to patterns of cultural demand. This method accounts for varied user activity scales, offering a refined spatial analysis of demand across Beijing.

Demand-Supply Interaction Model

The study builds a Demand-Supply Ratio (DSR) for different cultural patterns identified via TLDA. DSR maps highlight urban areas with skewed demand-supply balance, indicating where cultural infrastructure investments are necessary. The analysis correlates DSR with actual travel distances users undertake, providing empirical validation for prioritizing resource allocation.

Results and Implications

The resulting maps from TLDA and demand-supply interaction analyses reveal significant disparities in cultural resource distribution. Urban areas with high DSR are often linked to increased travel needs for cultural engagement, demonstrating a pivotal leverage point for urban policy makers and cultural planners.

Conclusion

This study underscores the potential of integrating mobile social network data with advanced topic modeling to inform urban cultural planning. It champions a data-driven methodology that dynamically aligns urban infrastructure development with actual cultural trends and resident preferences. The framework presents a scalable solution to other metropolises seeking to optimize cultural resource distribution in line with empirical user activity data. The case study of Beijing not only provides insights for local policy but also sets a precedent for leveraging digital trail data in global urban planning contexts.