Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning

By Chao Zhang, Keyang Zhang, Quan Yuan, Haoruo Peng, Yu Zheng, T. Hanratty, Shaowen Wang, Jiawei Han. 2017

151 citations recorded by the source corpus.

With the ever-increasing urbanization process, systematically modeling people's activities in the urban space is being recognized as a crucial socioeconomic task. This task was nearly impossible years ago due to the lack of reliable data sources, yet the emergence of geo-tagged social media (GTSM) data sheds new light on it. Recently, there have been fruitful studies on discovering geographical topics from GTSM data. However, their high computational costs and strong distributional assumptions about the latent topics hinder them from fully unleashing the power of GTSM. To bridge the gap, we present CrossMap, a novel cross-modal representation learning method that uncovers urban dynamics with massive GTSM data. CrossMap first employs an accelerated mode seeking procedure to detect spatiotemporal hotspots underlying people's activities. Those detected hotspots not only address spatiotemporal variations, but also largely alleviate the sparsity of the GTSM data. With the detected hotspots, CrossMap then jointly embeds all spatial, temporal, and textual units into the same space using two different strategies: one is reconstruction-based and the other is graph-based. Both strategies capture the correlations among the units by encoding their co-occurrence and neighborhood relationships, and learn low-dimensional representations to preserve such correlations. Our experiments demonstrate that CrossMap not only significantly outperforms state-of-the-art methods for activity recovery and classification, but also achieves much better efficiency.

Subfields: Geography, Planning and Development, Transportation, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Geography, Planning and Development

In Transportation

In Signal Processing

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “[83] embed the geo-tagged social media (GTSM) records < time, location, message> which enables them to recover the missing component from a GTSM triplet given the other two.”
Network Representation Learning: A Survey (2017, background): “theway for awide range of network analytic tasks to be easily and efficiently tackled in the new vector space, such as node classification [10], [11], link prediction [12], [13], clustering [2], recommendation [14], [15], similarity search [16], and visualization [17].”
Bridging Collaborative Filtering and Semi-Supervised Learning: A Neural Approach for POI Recommendation (2017, background): “While traditional recommender systems mostly work with ratings and reviews [20], POI recommendations naturally come with various context, such as geographical information [24, 25, 28, 47, 49], categorical information [53, 55], social information [22, 38, 50, 52], temporal information [48, 56], etc.”
Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning (2020, background): “Many works are trying to ﬁnd some patterns and correlations from spatio-temporal datasets [17], [31], [32].”
Attributed Social Network Embedding (2017, background): “It is reported that over 45% tweets contain images in Weibo [51], making it urgent and meaningful to perform network embedding with multi-modal data [52].”