The Role of Data Science and Volunteered Geographic Information in Enhancing Government Service Delivery: Opportunities and Challenges

Machine Learning and Data Science Techniques for Effective Government Service Delivery

Introduction

The delivery of public services has been transformed in recent years by the incorporation of technology and data-driven strategies. The application of Volunteered Geographic Information (VGI) with Data Science is a noteworthy development in this field. VGI is the term used to describe location-based data that people voluntarily share on different digital platforms (Goodchild, 2007), such as social media, mobile apps, and crowdsourcing projects. Whereas, data science refers to the procedures and strategies for extracting conclusions and information from huge datasets (Brodie, 2019; Provost & Fawcett, 2013).

Due to a number of reasons, the use of VGI and data science in the delivery of public services has significantly increased. Firstly, there is an unprecedented amount of location-based data being collected and disseminated because of the expanding availability of mobile devices and the Internet availability (Huang et al., 2021). Nowadays, citizens can contribute to the creation of geographic data, offering important insights into their needs, preferences, and experiences (Goodchild, 2007). Secondly, traditional data collection techniques are expensive and time-consuming. VGI, in comparison, provides a real-time, cost-effective substitute that enables public sector organizations to acquire reliable information for decision-making procedures (Ahmad et al., 2022).

Informed and data-driven policy formation is made possible by the effective analysis and interpretation of large datasets available by the combination of VGI and data science (Arnaboldi & Azzone, 2020; Provost & Fawcett, 2013; Wong & C. Hinnant, 2022). As a result, public service providers can strengthen resource allocation, increase the effectiveness of their services, and cater to the unique requirements of the communities they serve. For example, poverty at the village level can be assessed by combining various data sources, including high-resolution imagery (HRI), point-of-interest (POI), OpenStreetMap (OSM), and digital surface model (DSM) data (Hu et al., 2022). Similarly, Ma et al., (2022) proposed a rationality evaluation approach for the spatial distribution of public toilets in urban functional areas by using POI big data and OSM. Whereas, KUCUKALI et al., (2022) utilized open-source geospatial data, including OSM, to evaluate pedestrian accessibility to essential public services and facilities and Abdulkarim et al., (2014) developed a VGI application using Google Street View to invite people to contribute to the classification of roof materials to support energy efficiency initiatives.

To this effect, the primary objective of this chapter is to present to examine the use of volunteered geographic information and data science in the context of providing public services. It will explore the possible advantages and difficulties of integrating these two elements in different spheres of the public sphere. To achieve this objective, the chapter is structured as follows: Section two provides an in-depth exploration of VGI with a particular focus on its impact on public service delivery. Similarly, section three delves into the concept of data science and its potential in enhancing government services. In section four, the synergistic integration of VGI and data science across four key government sectors is examined. Section five is dedicated to addressing the challenges that arise in this context. Finally, the last section serves as the concluding remarks of the chapter, accompanied by future directions for further research.