Macross: Urban Dynamics Modeling based on Metapath Guided Cross-Modal Embedding

TL;DR

Macross is a novel metapath-guided embedding model that effectively captures urban dynamics by integrating location, time, and text data from social media, enabling improved city planning and activity analysis.

Contribution

The paper introduces Macross, a scalable, cross-modal embedding approach that overcomes computational limitations of previous models by leveraging metapath2vec on heterogeneous urban data.

Findings

Outperforms state-of-the-art models in query relevance.

Achieves better activity recovery and classification accuracy.

Demonstrates scalability on large urban datasets.

Abstract

As the ongoing rapid urbanization takes place with an ever-increasing speed, fully modeling urban dynamics becomes more and more challenging, but also a necessity for socioeconomic development. It is challenging because human activities and constructions are ubiquitous; urban landscape and life content change anywhere and anytime. It's crucial due to the fact that only up-to-date urban dynamics can enable governors to optimize their city planning strategy and help individuals organize their daily lives in a more efficient way. Previous geographic topic model based methods attempt to solve this problem but suffer from high computational cost and memory consumption, limiting their scalability to city level applications. Also, strong prior assumptions make such models fail to capture certain patterns by nature. To bridge the gap, we propose Macross, a metapath guided embedding approach to jointly model location, time and text information. Given a dataset of geo-tagged social media posts, we extract and aggregate location and time and construct a heterogeneous information network using the aggregated space and time. Metapath2vec based approach is used to construct vector representations for times, locations and frequent words such that co-occurrence pairs of nodes are closer in latent space. The vector representations will be used to infer related time, locations or keywords for a user query. Experiments done on enormous datasets show our model can generate comparable if not better quality query results compared to state of the art models and outperform some cutting-edge models for activity recovery and classification.