Water Relationships in the U.S. Southwest: Characterizing Water Management Networks Using Natural Language Processing

John Murphy,Jonathan Ozik,Drew Cason,Paula Williams,Nicholson Collier,Richard Lammers,Mark Altaweel,Lilian Alessa,Andrew Kliskey

doi:10.3390/w6061601

Abstract

Natural language processing (NLP) and named entity recognition (NER) techniques are applied to collections of newspaper articles from four cities in the U.S. Southwest. The results are used to generate a network of water management institutions that reflect public perceptions of water management and the structure of water management in these areas. This structure can be highly centralized or fragmented; in the latter case, multiple peer institutions exist that may cooperate or be in conflict. This is reflected in the public discourse of the water consumers in these areas and can, we contend, impact the potential responses of management agencies to challenges of water supply and quality and, in some cases, limit their effectiveness. Flagstaff, AZ, Tucson, AZ, Las Vegas, NV, and the Grand Valley, CO, are examined, including more than 110,000 articles from 2004–2012. Documents are scored by association with water topics, and phrases likely to be institutions are extracted via custom NLP and NER algorithms; those institutions associated with water-related documents are used to form networks via document co-location. The Grand Valley is shown to have a markedly different structure, which we contend reflects the different historical trajectory of its development and its current state, which includes multiple institutions of roughly equal scope and size. These results demonstrate the utility of using NLP and NER methods to understanding the structure and variation of water management systems.

Highlights

The structural relationships among the public and private organizations that manage water can shape and constrain a population’s responses to socio-environmental challenges
Our theoretical framework has two central elements: the contention that the network of water management matters and the contention that public media sources contain a reflection of this structure, which we can capture through a data mining technique and which we can use for further, useful analysis
The results presented here demonstrate that natural language processing and network analyses can capture significant differences between water systems in the four assessed areas

Summary

Introduction

The structural relationships among the public and private organizations that manage water can shape and constrain a population’s responses to socio-environmental challenges. These institutions can vary in the spatial scale at which they are able to undertake action and can have competing or contradictory motives that restrict or even thwart cooperation or collective action. We present a method for the use of data mining on open and published information sources to recover the significant water management entities within a region and map their mutual relationships. The result is a condition in which multiple institutions must interact to manage diverse aspects of a single resource

Methods

Discussion

Conclusion