Geotagging tweets to landmarks using Convolutional Neural Networks with text and posting time

Kwan Hui Lim, Shanika Karunasekera, Aaron Harwood, Yasmeen George

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review

3 Citations (Scopus)


Geotagged tweets serve many important applications, e.g., crisis management, but only a small proportion of tweets are explicitly geotagged. We propose a Convolutional Neural Network (CNN) architecture for geotagging tweets to landmarks, based on the text in tweets and other meta information, such as posting time and source. Using a dataset of Melbourne tweets, experimental results show that our algorithm out-performed various state-of-the-art baselines.

Original languageEnglish
Title of host publicationProceedings of IUI 2019
EditorsOliver Brdiczka, Gaelle Calvary, Polo Chau
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages2
ISBN (Electronic)9781450366731
Publication statusPublished - 2019
Externally publishedYes
EventInternational Conference on Intelligent User Interfaces 2019 - Los Angeles, United States of America
Duration: 16 Mar 201920 Mar 2019
Conference number: 24th


ConferenceInternational Conference on Intelligent User Interfaces 2019
Abbreviated titleIUI 2019
Country/TerritoryUnited States of America
CityLos Angeles
Internet address


  • Geolocation
  • Geotagging
  • Neural networks
  • Twitter

Cite this