Public Opinion Mining for Governmental Decisions

Abstract

eGovernment refers to the use of information and communications technologies (ICTs) to improve the quality of services and information offered to citizens, to make government more accountable to citizens and advance public sector transparency. As already pointed out by other researchers, one of the most important issues for making eGovernment effective is to enable citizens to participate in the decision‑making process. Nowadays, topics related to governmental decisions are among the most widely discussed ones within digital societies. This is not only because web 2.0 has empowered people with the ability to communicate remotely but also because governments all around the globe publish a great volume of their decisions and regulations online. In this paper, we propose the exploration of text and data mining techniques towards capturing the public’s opinion communicated online and concerning governmental decisions. The objective of our study is twofold and focuses on understanding the citizen opinions about eGovernment issues and on the exploitation of these opinions in subsequent governmental actions. We examine several features in the user‑generated content discussing governmental decisions in an attempt to automatically extract the citizen opinions from online posts dealing with public sector regulations and thereafter be able to organize the extracted opinions into polarized clusters. Our goal is to be able to automatically identify the public’s stance against governmental decisions and thus be able to infer how the citizens’ viewpoints may affect subsequent government actions. To demonstrate the usability and added value of our proposed approach we have designed an interactive eGovernment infrastructure, the architecture of which we will present and discuss in our paper. Moreover, we will elaborate on the system details, its adaptation capacity and we will discuss its usage benefits for both citizens and public sector bodies.