Location Estimation Using Crowdsourced Geospatial Narratives

TL;DR

This paper presents a novel method to estimate object locations by extracting and quantifying spatial relationships from user-generated textual narratives, such as travel blogs, using an EM algorithm for triangulation.

Contribution

It introduces a new approach to derive geospatial information from qualitative textual data and estimates object locations without relying on traditional coordinate data.

Findings

High accuracy in location estimation demonstrated

Effective extraction of spatial relationships from narratives

Triangulation based on EM algorithm improves geospatial reasoning

Abstract

The "crowd" has become a very important geospatial data provider. Subsumed under the term Volunteered Geographic Information (VGI), non-expert users have been providing a wealth of quantitative geospatial data online. With spatial reasoning being a basic form of human cognition, narratives expressing geospatial experiences, e.g., travel blogs, would provide an even bigger source of geospatial data. Textual narratives typically contain qualitative data in the form of objects and spatial relationships. The scope of this work is (i) to extract these relationships from user-generated texts, (ii) to quantify them and (iii) to reason about object locations based only on this qualitative data. We use information extraction methods to identify toponyms and spatial relationships and to formulate a quantitative approach based on distance and orientation features to represent the latter. Positional probability distributions for spatial relationships are determined by means of a greedy Expectation Maximization-based (EM) algorithm. These estimates are then used to "triangulate" the positions of unknown object locations. Experiments using a text corpus harvested from travel blog sites establish the considerable location estimation accuracy of the proposed approach.