Most water utilities have to handle a substantial number of customer complaints every year. Traditionally, complaints are handled by skilled staff who know how to identify primary issues, classify complaints, find solutions, and communicate with customers. The effort associated with complaint processing is often great, depending on the number of customers served by a water utility. However, the rise of natural language processing (NLP), enabled by deep learning, and especially the use of deep recurrent and convolutional neural networks, has created new opportunities for comprehending and interpreting text complaints. As such, we aim to investigate the value of the use of NLP for processing customer complaints. Through a case study about the Water Utility Groningen in the Netherlands, we demonstrate that NLP can parse language structures and extract intents and sentiments from customer complaints. As a result, this study represents a critical and fundamental step toward fully automating consumer complaint processing for water utilities.

@en

The water sector is, currently and for the foreseeable future, challenged by rising levels of uncertainty in demand and availability of water, in a context of aging infrastructure and limited investment. In order to support strategic planning, water companies need a way to assess how their system behaves when faced with a range of changing conditions (climatic trends, asset deterioration, behavioral patterns, etc.) as well as accidents/incidents and/or extreme events (wildcards). In this study, a resilience assessment methodology was demonstrated, with 'stress tests' alternative water system configurations (including systems designed with decentralized or distributed philosophies) under a range of scenarios and extreme events. A 'resilience profile graph' was developed to quantify the performance of each configuration. The methodology was applied to the real-world urban water system of Oasen, which supplies the eastern part of the Province of South Holland, where the current system configuration and two potential future configurations were tested (one decentralized and one distributed). We show how the concept of resilience, operationalized through this methodology, can assist long term decision making and support strategic infrastructure planning.@en