The ACM International Conference on Advances in Geographic Information Systems 2024 (ACM SIGSPATIAL 2024) will be held on Oct. 29 – Nov. 1, 2024 in Atlanta, USA. The following presentations will be delivered.

1. Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reports

Forecasting rail congestion is crucial for efficient mobility in trans- port systems. We present rail congestion forecasting using reports from passengers collected through a transit application. Although reports from passengers have received attention from researchers, ensuring a sufficient volume of reports is challenging due to pas- senger’s reluctance. The limited number of reports results in the sparsity of the congestion label, which can be an issue in build- ing a stable prediction model. To address this issue, we propose a semi-supervised method for congestion forecasting for trains, or SURCONFORT. Our key idea is twofold: firstly, we adopt semi- supervised learning to leverage sparsely labeled data and many unlabeled data. Secondly, in order to complement the unlabeled data from nearby stations, we design a railway network-oriented graph and apply the graph to semi-supervised graph regularization. Empirical experiments with actual reporting data show that SURCONFORT improved the forecasting performance by 14.9% over state-of-the-art methods under the label sparsity.

2. Are Crowded Events Forecastable from Promotional Announcements with Large Language Models?

Forecasting the number of visitors at a public event, termed event crowd forecasting (ECF), has recently garnered attention due to its social significance. Although existing ECF methods have pio- neered successful feature design by considering event contents with contexts (e.g., weather, type of day, time), their scalability across different event types is limited due to the necessity of costly feature engineering. To address this issue, we propose a novel ECF frame- work, named EventOutlook. Based on our observation of various events, online event announcements indicate the factors that induce crowded events. Thus, we incorporate event announcements into ECF methods. To handle such unstructured data, which have no unified format among events, we leverage large language models (LLM) to extract crowding factors and embed them into an LLM-driven crowding-indicator feature (LCIF). Empirical experiments with real- world event data show that EventOutlook significantly improved ECF performance compared to state-of-the-art methods.

For the detailed contents of this research project, please see the corresponding project page.

— Presentation information —

Poster/Demo Session (Wed., Oct. 30, 2024, 16:30 PM – 24:00 PM EDT) (Program)

Soto Anno, Kota Tsubouchi, and Masamichi Shimosaka.
Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reports.
SIGSPATIAL’24: Proceedings of the 32nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2024), Atlanta, GA, USA, Oct. 29 – Nov. 1. 2024.

Soto Anno, Dario Tenore, Kota Tsubouchi, and Masamichi Shimosaka.
Are Crowded Events Forecastable from Promotional Announcements with Large Language Models?
SIGSPATIAL’24: Proceedings of the 32nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2024), Atlanta, GA, USA, Oct. 29 – Nov. 1. 2024.