Predicting People’s Home Location From Sparse Footprints

Lead Investigators

• Hamdi Kavak
• Jose Padilla (Advisor)

Student and Senior Collaborators

• Daniele Vernon-Bido (Collaborator student 2017-2018)

Project Dates

2017-2018

Summary

This study develops a machine learning classifier that determines Twitter users’ home location with 100 meters resolution. Our results suggested up to 0.87 overall accuracies in predicting home location for the City of Chicago. We explored the influence of the time span of data collection and the location-sharing habits of a user. The classifier accuracy changes by data collection time but larger than one-month periods do not significantly increase prediction accuracy. An individual’s home location can be ascertained with as few as 0.6 to 1.4 tweets/day or 75 to 225 tweets with an accuracy of over 0.8. Our results shed light on how home location information can be predicted with high accuracy and how long data must be collected. On the flip side, our results imply potential privacy issues on publicly available social media data.

Publications & Presentations

• Fine-Scale Prediction of People’s Home Location using Social Media Footprints
  H. Kavak, D. Vernon-Bido and J.J. Padilla
  SBP-BRIMS Conference 2018, Washington, DC, July 10-13, 2018
  [Paper] [BibTex]

Funding

• The Office of the Assistant Secretary of Defense for Research and Engineering (OASD(R&E)) under agreement number FAB750-15-2-0120.

Last updated on Jan 27, 2022.