Text mining for the evaluation of public services: the case of a public bike-sharing system

  • PDF / 889,343 Bytes
  • 17 Pages / 439.37 x 666.142 pts Page_size
  • 85 Downloads / 309 Views

DOWNLOAD

REPORT


Text mining for the evaluation of public services: the case of a public bike‑sharing system Na Rang Kim1 · Soon Goo Hong1  Received: 5 June 2020 / Accepted: 17 June 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract This study conducted text mining analysis of the review text data (13,615 accounts) posted on SNS by users of the public bike-sharing service in South Korea. A total of 11,954 reviews were processed with SKT KoBERT and classified them either positive or negative. Subsequently, various text mining techniques were used to determine the factors affecting the users’ polarity. The study results revealed that the identification of the positive and negative factors affecting service quality through an analysis of reviews by text mining contributes to the improvement of the public bike-sharing system. Keywords  Public service evaluation · Text mining · Deep learning · Public bikesharing system

1 Introduction The wide availability of smart devices has empowered the voice of citizens in the public service sector, as people can easily express their opinions or demands. Public service providers can also use this communication channel to effectively collect data on citizens’ needs and perceptions regarding various services and subsequently develop strategies to improve the service quality. For example, in France, the Commission National du Débat Public was established to reflect public opinions on large-scale national projects carried out by the government (Eun 2016). The most important aim of public services is to provide efficient and convenient services that ensure a quality environment to the citizens (Oh 2011). Lucy et al. (1977) defined public services as “social, economic, and political activities that * Soon Goo Hong [email protected] Na Rang Kim [email protected] 1



Department of Management Information Systems, Dong-A University, 225 Gudeok‑ro, Seo‑gu, Pusan 49236, Republic of Korea

13

Vol.:(0123456789)



N. Kim, S. Hong

distribute the benefits in society.” They categorized public services as routine services, protective services, and developmental services based on social functions. First, routine services refer to those that most people use frequently in their daily lives; these include water and sewage, garbage collection, and public transportation. Second, protective services refer to ones that maintain public order and protecting people and property; these include safety, security, firefighting, justice, and disaster protection. Third, developmental services refer to ones that enable individuals to develop their physical, intellectual, and psychological potential; including education, parks, leisure, public health, and public assistance. Traditionally, the success of public service provision is evaluated by assessing the citizens’ satisfaction with the efficiency and quality of the services by experts’ analyses of survey data. The survey method is widely practiced because it allows direct investigation of the items of interest. However, the method also has a number