Tweeting Behaviour during Train Disruptions within a City

Limsopatham, N., Albakour, M.-D., Macdonald, C. and Ounis, I. (2015) Tweeting Behaviour during Train Disruptions within a City. In: Workshop on Digital Placemaking: Augmenting Physical Places with Contextual Social Data, Oxford, 26 May 2015,

Abstract

In a smart city environment, citizens use social media for communicating and reporting events. Existing work has shown that social media tools, such as Twitter and Facebook, can be used as social sensors to monitor events in real-time as they happen (e.g. riots, natural disasters and sport events). In this paper, we study the reactions of citizens in social media towards train disruptions within a city. Our study using 30 days of tweets in a large city shows that citizens react differently to train disruptions by, for instance, displaying unique behaviours in tweeting depending on the time of the disruption. Specifically, for working days, tweets related to train disruptions are typically generated during rush hour periods. In contrast, during weekends, urban citizens tended to tweet about train disruptions during late evenings. Using these insights, we develop a supervised approach to predict whether a train disruption tweet will be retweeted and propagated on the social network, by using features, such as time, user, and the content of tweets. Our experimental results show that we can effectively predict when a train disruption tweet is retweeted by using such features.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Limsopatham, Mr Nut and Macdonald, Professor Craig and Albakour, Dr M-Dyaa and Ounis, Professor Iadh
• Authors: Limsopatham, N., Albakour, M.-D., Macdonald, C., and Ounis, I.
• College/School: College of Science and Engineering > School of Computing Science
• Copyright Holders: Copyright © 2015 Association for the Advancement of Artificial Intelligence
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher.

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
65192	1	Urban Big Data Research Centre	Piyushimita Thakuriah	Economic & Social Research Council (ESRC)	ES/L011921/1	SPS - URBAN STUDIES