Urban Crowdsensing using Social Media: An Empirical Study on Transformer and Recurrent Neural Networks
This work aims to provide a low-cost, scalable alternative to physical sensors for urban planners to understand crowd levels and detect events, which is an incremental improvement over existing methods.
This paper explores the use of publicly available social media data from Twitter and Flickr to address urban sensing problems, specifically event detection and crowd level prediction. They collected a dataset with ground truth events and used neural network models to classify event-related posts and regression models to predict crowd levels based on post counts.
An important aspect of urban planning is understanding crowd levels at various locations, which typically require the use of physical sensors. Such sensors are potentially costly and time consuming to implement on a large scale. To address this issue, we utilize publicly available social media datasets and use them as the basis for two urban sensing problems, namely event detection and crowd level prediction. One main contribution of this work is our collected dataset from Twitter and Flickr, alongside ground truth events. We demonstrate the usefulness of this dataset with two preliminary supervised learning approaches: firstly, a series of neural network models to determine if a social media post is related to an event and secondly a regression model using social media post counts to predict actual crowd levels. We discuss preliminary results from these tasks and highlight some challenges.