Journal cover Journal topic
Abstracts of the ICA
Journal topic
Volume 1
Abstr. Int. Cartogr. Assoc., 1, 160, 2019
https://doi.org/10.5194/ica-abs-1-160-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Abstr. Int. Cartogr. Assoc., 1, 160, 2019
https://doi.org/10.5194/ica-abs-1-160-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  15 Jul 2019

15 Jul 2019

Social Media for Sensing: Do Tweets Represent Events at Geo-Tagged Locations?

Morteza Karimzadeh Morteza Karimzadeh
  • Purdue Visualization and Analytics Center (PURVAC), School of Electrical and Computer Engineering, Purdue University, USA

Keywords: social media, geoparsing, flow maps, geographic focus, geographic information retrieval, geovisualization

Abstract. It is difficult to quantify how – and to what extent – the public engages with events in other countries. Twitter users all over the globe post more than 500 million tweets every day. They also discuss places in their tweets. Therefore, Twitter provides a lens through which geographic research can investigate public discourse as it relates to place. Further, many research studies use geo-tagged posts on Twitter (and social media in general) to sense the society in particular locations (according to geo-tags) for various purposes that may need a “local sense” such as sentiment analysis, situational awareness for crisis response, election prediction, or targeted advertising. However, it is unclear to what extent the online discourse by users are about local events versus events in other locations or countries.

In this pilot study, we visualize and characterize relations between places mentioned in Twitter posts and places where users live to identify whether Twitter users in different countries engage more with domestic or international (or transnational) events. We also visualize the extent to which places in other countries are being discussed through online platforms/social media. The results have implications for the design of algorithms in geographic information science attempting to automatically geolocate places mentioned in tweets for use in sentiment or spatial analysis, situational awareness, and advertisement. Additionally, most place names are ambiguous and refer to more than one location. For example, London can refer to London, Texas or London in England. Our analysis gauge whether Twitter users’ profile locations can be used to disambiguate places that are mentioned in their tweets.

Publications Copernicus
Download
Citation