Improving public services by mining citizen feedback: An application of natural language processing

Abstract

Research on user satisfaction has increased substantially in recent years. To date, most studies have tested the significance of predefined factors thought to influence user satisfaction, with no scalable means of verifying the validity of their assumptions. Digital technology has created new methods of collecting user feedback where service users post comments. As topic models can analyse large volumes of feedback, they have been proposed as a feasible approach to aggregating user opinions. This novel approach has been applied to process reviews of primary care practices in England. Findings from an analysis of more than 200,000 reviews show that the quality of interactions with staff and bureaucratic exigencies are the key drivers of user satisfaction. In addition, patient satisfaction is strongly influenced by factors that are not measured by state-of-the-art patient surveys. These results highlight the potential benefits of text mining and machine learning for public administration.