Urban research has long recognized that neighbourhoods are dynamic and relational. However, lack of data, methodologies, and computer processing power have hampered a formal quantitative examination of neighbourhood relational dynamics. To make progress on this issue, this study proposes a graph neural network (GNN) approach that permits combining and evaluating multiple sources of information about internal characteristics of neighbourhoods, their past characteristics, and flows of groups among them, potentially providing greater expressive power in predictive models. By exploring a public large-scale dataset from Yelp, we show the potential of our approach for considering structural connectedness in predicting neighbourhood attributes, specifically to predict local culture. Results are promising from a substantive and methodologically point of view. Substantively, we find that either local area information (e.g. area demographics) or group profiles (tastes of Yelp reviewers) give the best results in predicting local culture, and they are nearly equivalent in all studied cases. Methodologically, exploring group profiles could be a helpful alternative where finding local information for specific areas is challenging, since they can be extracted automatically from many forms of online data. Thus, our approach could empower researchers and policy-makers to use a range of data sources when other local area information is lacking.

翻译：城市研究长期以来认识到社区是动态且具有关系性的。然而，数据、方法论和计算机处理能力的缺乏阻碍了对社区关系动态的正式定量研究。为解决这一问题，本研究提出一种图神经网络方法，该方法允许整合和评估关于社区内部特征、历史特征以及群体间流动的多种信息来源，从而可能为预测模型提供更强的表达能力。通过探索Yelp的公开大规模数据集，我们展示了该方法在考虑结构连接性方面预测社区属性（特别是预测地方文化）的潜力。从实质和方法论角度看，结果均具有前景。实质性方面，我们发现无论是局部区域信息（如区域人口统计数据）还是群体特征（Yelp评论者的品味），在预测地方文化时均能提供最佳结果，且在研究的全部案例中效果几乎等同；方法论方面，当特定区域的局部信息难以获取时，探索群体特征可作为一种有用的替代方案，因为这些特征可从多种形式的在线数据中自动提取。因此，当缺乏其他局部区域信息时，我们的方法能支持研究人员和政策制定者利用多种数据来源。