Application of Natural Language Processing to Determine User Satisfaction in Public Services

Research on user satisfaction has increased substantially in recent years. Studies to date tend to test for significance of pre-defined factors thought to have an influence with no scalable means to verify the validity of the assumptions made. Digital technology has enabled new methods to collect user feedback, for example through online forums where service users post comments. Topic models can help analyze large volumes of such feedback and are proposed as a feasible solution to aggregate user opinions for use in the public sector. Insights can contribute to a more inclusive decision-making process in public services. This novel approach is applied to process reviews of publicly-funded primary care practices in England. Findings from the analysis of over 200,000 reviews indicate that the quality of interactions with staff and bureaucratic exigencies are the key drivers of user satisfaction. Moreover, patient satisfaction is strongly influenced by factors not considered in state-of-the-art patient surveys. These results highlight the potential benefits that text mining and machine learning for the public administration field