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


Negar Hassanpour


Goldstream Publishing Inc.


Computer science


Information and communications technologies


University of Northern British Columbia



Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects