Files in this item



application/pdfWang-Yuanyuan_20180416_V01.pdf (157kB)
(no description provided)PDF


Title:Detecting Train Delays using Railway Network Topology in Twitter
Author(s):Wang, Yuanyuan; Nakaoka, Yusuke; Siriaraya, Panote; Kawai, Yukiko; Akiyama, Toyokazu
Subject(s):topic propagation
railway topology
delay detection
real space and cyberspace
Abstract:This paper presents a novel train delay detection method based on topic propagation analysis of geo-tagged tweets between railway stations. Our goal is to detect traffic accidents and to predict train delays in railway network topology by tracing how relevant tweets propagate in real space and cyberspace. In our method, we utilize railway network as the topology of real space, and extract the topology of social network that is mapped on the railway network. This permits observing the influence of delays on stations with a few tweets, or predicting related tweets of affected stations even if the tweets contain indirect topics about delays.
Issue Date:2018
Series/Report:iConference 2018 Proceedings
Genre:Conference Poster
Rights Information:Copyright 2018 is held by Yuanyuan Wang, Yusuke Nakaoka, Panote Siriaraya, Yukiko Kawai, Toyokazu Akiyama. Copyright permissions, when appropriate, must be obtained directly from the authors.
Date Available in IDEALS:2018-07-12

This item appears in the following Collection(s)

Item Statistics