A Google Trends spatial clustering approach for a worldwide Twitter user geolocation

作者：

Highlights：

• We target the worldwide coordinate-level location of Twitter users

• We propose a novel Google Trends noun (GTN) spatial clustering approach

• GTN only uses historical tweets and public Web data (e.g., Google Trends)

• We collected a recent Twitter dataset with ground truth locations of 3,268 users

• The best overall results were achieved by the GTN DSCAN (GTN-DB) method

摘要

•We target the worldwide coordinate-level location of Twitter users•We propose a novel Google Trends noun (GTN) spatial clustering approach•GTN only uses historical tweets and public Web data (e.g., Google Trends)•We collected a recent Twitter dataset with ground truth locations of 3,268 users•The best overall results were achieved by the GTN DSCAN (GTN-DB) method

论文关键词：City-level geolocation,Clustering,Google Trends,Natural language processing,Twitter

论文评审过程：Received 15 January 2020, Revised 20 May 2020, Accepted 23 May 2020, Available online 12 June 2020, Version of Record 12 June 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102312