Exploring Regional Variation in Spatial Language Using Spatially Stratified Web-Sampled Route Direction Documents

Sen Xu, Alexander Klippel, Alan M. MacEachren, Prasenjit Mitra

Research output: Contribution to journalArticle

3 Citations (Scopus)


Spatial language, such as route directions, can be analyzed to shed light on how humans communicate and conceptualize spatial knowledge. This article details a computational linguistic approach using route directions to study regional variations in spatial language. We developed a web-sourcing approach to collect human-generated route direction documents on a geographical scale. Specifically, we built the Spatially strAtified Route Direction (SARD) Corpus through automated scraping, classifying, and georeferencing of route directions. Based on semantic categories of cardinal and relative direction terms, the analysis of the SARD Corpus reveals significant differences and patterns on both national (United States, United Kingdom, and Australia) and regional (contiguous U.S. states) levels. Combining computational linguistics and georeferencing approaches offers the potential for extending classic spatial linguistic studies.

Original languageEnglish
Pages (from-to)255-283
Number of pages29
JournalSpatial Cognition and Computation
Issue number4
Publication statusPublished - 2 Oct 2014
Externally publishedYes



  • cardinal vs. relative direction
  • corpus linguistics
  • georeferenced web sampling
  • regional linguistic difference
  • spatial language analysis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Modelling and Simulation
  • Earth-Surface Processes
  • Experimental and Cognitive Psychology

Cite this