Location Inference for Non-Geotagged Tweets in User Timelines [Extended Abstract]

Pengfei Li, Hua Lu, Nattiya Kanhabua, Sha Zhao, Gang Pan

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

This study explores the problem of inferring locations for individual tweets. We scrutinize Twitter user timelines in a novel fashion. First of all, we split each user's tweet timeline temporally into a number of clusters, each tending to imply a distinct location. Subsequently, we adapt machine learning models to our setting and design classifiers that classify each tweet cluster into one of the pre-defined location classes at the city level. Extensive experiments on a large set of real Twitter data suggest that our models are effective at inferring locations for non-geotagged tweets and outperform the state-of-the-art approaches significantly in terms of inference accuracy.
Original languageEnglish
Title of host publication35th IEEE International Conference on Data Engineering, ICDE 2019
Number of pages2
PublisherIEEE
Publication date2019
Pages2111-2112
ISBN (Print)978-1-5386-7475-8
ISBN (Electronic)978-1-5386-7474-1
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event35th International Conference on Data Engineering (ICDE) - Macau, China
Duration: 8 Apr 201911 Apr 2019
Conference number: 35
https://www.computer.org/csdl/proceedings/icde/2019/1aDSOMTGCIw

Conference

Conference35th International Conference on Data Engineering (ICDE)
Number35
Country/TerritoryChina
CityMacau
Period08/04/201911/04/2019
Internet address
SeriesIEEE Transactions on Knowledge and Data Engineering
ISSN1041-4347

Keywords

  • Twitter
  • Location inference
  • Bayes
  • LSTM

Cite this