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.

Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation

“…Dirichlet allocation (TLDA) [36] in this section to mine the inner interests of users from a more general perspective. The TLDA model is an unsupervised machine learning algorithm that characterises each user as a mixture of patterns with both venue and temporal preferences considered.…”

“…• GeoMF [17] This method extends the MF by augmenting latent factors with the user's activity region and POI's influence area. • TLDA [36] TLDA is an extension model of LDA that can be applied to extract users' lifestyle patterns with temporal preferences considered. It is also employed as the topic module in our framework to enhance memory network.…”

Deconstructing laws of accessibility and facility distribution in cities

“…Forwardlooking approaches for planning facilities in cities would also consider individuals' preferences to facilities via mining mobility patterns. Zhou et al (24) introduced a location-based social network dataset to derive the demand for different types of cultural resources and identified the urban regions with lack of venues. While efforts have been devoted to address the optimal allocation problem in specific cities (24)(25)(26)(27), systematic understanding of the optimal distribution of facilities is still lacking from the urban science perspective.…”

Urban Functional Area Division Based on Cell Tower Classification

“…In order to make the planning and construction of the city more conducive to its citizens, the division of urban functional areas is a key point for urban planners to take into consideration [1]. Since human mobility has high regularities [2]- [5], and it can well reflect the functional areas of the city to some extent [6], [7], the study of the human mobility patterns has become a hot topic [8]- [13]. In the past several years, surveys of urban functional areas are mostly relied on field trips.…”

“…The temporal and spatial attributes are added to the original LDA algorithm to obtain our TS-LDA (Temporal and Spatial Latent Dirichlet Allocation algorithm), which can be applied to time and space classification. At the same time, the TCV (Temporal Coherence Value) evaluation algorithm [6] is used to provide an evaluation standard for TS-LDA. In this paper, we use OIDD data from Beijing and Zhuhai as the basic dataset.…”