Urban Crowdsensing using Social Media: An Empirical Study on Transformer and Recurrent Neural Networks

TL;DR

This paper explores using social media data from Twitter and Flickr to detect events and predict crowd levels in urban areas, offering a cost-effective alternative to physical sensors through neural network models.

Contribution

It introduces a new social media dataset for urban sensing and demonstrates initial neural network approaches for event detection and crowd prediction.

Findings

Neural networks can classify social media posts related to events.

Social media post counts can be used to predict crowd levels.

Challenges in data quality and model accuracy are discussed.

Abstract

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.