The algorithmic processing of written language for tools such as predictive text, sentiment analysis and translation services has become commonplace. The segment of computer science concerned with the interpretation of human language, NLP (Natural Language Processing), is a versatile and developing field. In this paper, NLP is deployed unconventionally for a new use: gathering insights into a building’s seismic exposure characteristics and classifying it according to the Global Earthquake Model (GEM) taxonomy. 

NLP is used in this study to ‘read’ the contents of digitally-submitted Planning Applications (PA’s) made on the Maltese archipelago. Maltese architects are required to submit a concise but detailed description of the proposed works on any given site as part of a planning process. It is suggested that useful insights exist within this description that can assist in classifying buildings within the bounds of the GEM taxonomy.

NLP can be used to layer additional information onto existing exposure models founded on more conventional data. Most critically, it may be possible for NLP-derived insights to update existing exposure models by understanding the gradual changes to the built environment, thus allowing to model the so-called “dynamic exposure”. NLP may prove a useful new tool for exposure modeling.