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

EasyChair Preprint 1103

Abstract

Research on user satisfaction has increased substantially in recent years. However, the relative importance and relationships between different determinants of satisfaction remains uncertain. Moreover, quantitative studies to date tend to test for significance of pre-determined factors thought to have an influence with no scalable means to identify other causes of user satisfaction. Meanwhile, digital technology development has enabled new methods to collect user feedback, for example through online forums where users can comment freely on their experience. New tools are needed to analyze large volumes of such feedback. The use of topic models is proposed as a feasible solution to aggregate open-ended user opinions that can easily be deployed in the public sector. This novel methodological approach is applied to a case of service reviews of publicly-funded primary care practices in England. Findings from the analysis of over 200,000 reviews covering almost 7,700 primary care centers indicate that the quality of interactions with staff and bureaucratic exigencies are the key issues driving user satisfaction across England. Moreover, patient satisfaction is strongly influenced by the quality of bureaucratic procedures and facilities, issue areas not considered in state-of-the-art patient surveys.

Keyphrases: AI, Natural Language Processing, user satisfaction

@booklet{EasyChair:1103,
  author    = {Radoslaw Kowalski and Marc Esteve and Slava Jankin Mikhaylov},
  title     = {Application of Natural Language Processing to Determine User Satisfaction in Public Services},
  howpublished = {EasyChair Preprint 1103},
  year      = {EasyChair, 2019}}