Using Natural Language Processing to Read Plans

Problem, research strategy, and findings Planners need to read plans learn adapt current practice. may struggle find time study lengthy planning documents, especially in emerging areas such as climate change urban resilience. Recently, natural language processing (NLP) has shown promise big textual data. We asked whether planners could use NLP techniques more efficiently extract useful reliable information from documents. By analyzing 78 resilience the 100 Resilient Cities Network, we found that results generated topic modeling, which is an technique, coincided a large extent (80%) with those conventional content analysis approach. Topic modeling was generally effective efficient extracting main of plans, whereas approach in-depth details but at expense considerable effort. further propose transferrable model for cutting-edge collection using machine learning. Our methodology limitations: Both can be subject human bias generate unreliable results; text create inaccurate due their specific method limitations; transferable only applied data where there are enough sufficiently long documents.Takeaway practice represents valuable addition planner’s toolbox. coupled other help effectively discover key topics identify priorities emphasis, relevant policies.