Mining geographic knowledge using location aware topic model

  • Authors:
  • Chong Wang;Jinggang Wang;Xing Xie;Wei-Ying Ma

  • Affiliations:
  • Microsoft Research Asia, Beijing, China;School of Mathematics & Computational Science: Sun Yat-Sen University, Guangzhou, China;Microsoft Research Asia, Beijing, China;Microsoft Research Asia, Beijing, China

  • Venue:
  • Proceedings of the 4th ACM workshop on Geographical information retrieval
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Most online activities are associated with geographical locations. For example, people write personal blogs about interesting places they have ever been to; read news about important local events; and search the web to find delicious restaurants. Mining geographical knowledge from these online activities can greatly benefit lots of web applications. In this paper, we propose a Location Aware Topic Model (LATM), a probabilistic graphical model, to explicitly model the relationships between locations and words. Experiments on several data sets, including news and blogs, showed satisfactory results.