Extending and refining the original automated text mining algorithm for an initial market trial

Text documents often include information pertaining to geographic locations. Mapping these place names to specific geographic locations currently requires a considerable amount of human effort to match the text with a GIS or other mapping system. This becomes especially challenging when the same place name is represented by multiple places, such as in the naming of waterbodies (e.g. lakes and rivers). To overcome this challenge, we propose a new algorithm that could improve the accuracy of geo-parsing applications, with the intention of testing this in a real world situation and evaluate these results.

Faculty Supervisor:

Dr. Liang Chen

Student:

Negar Hassanpour

Partner:

Goldstream Publishing Inc.

Discipline:

Computer science

Sector:

Information and communications technologies

University:

University of Northern British Columbia