Public Opinion Mining for Governmental Decisions

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 ad- vance 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 communi- cated online and concerning governmental decisions. The objective of our study is twofold and focuses on under- standing 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 de- cisions 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 capac- ity and we will discuss its usage benefits for both citizens and public sector bodies. In this paper, we try to fill this void by proposing a novel eGovernment mechanism that captures the societal impact of public sector regulations in an attempt to decipher the public"s stance towards gov- ernmental decisions. In particular, we propose the exploitation of data mining techniques towards firstly capturing the public"s opinions (communicated online) about governmental decisions and sec- ondly analysing the polarity of the mined opinions so that they are considered in subsequent govern- mental decisions. Specifically, we introduce a method for decomposing citizens" opinions and com- ments that are posted in online fora and blogs, in order to evaluate how governmental decisions are perceived by the public and thereafter how the public"s implicit feedback should be interpreted by governmental bodies in their subsequent actions. What motivates our study is that up-to-date gov-

[1]  Ruwei Dai,et al.  AMAZING: A sentiment mining and retrieval system , 2009, Expert Syst. Appl..

[2]  Linda A. Macaulay,et al.  A Collaboration Pattern Language for eParticipation: a Strategy for Reuse , 2009 .

[3]  Anne H. H. Ngu,et al.  Business-to-business interactions: issues and enabling technologies , 2003, The VLDB Journal.

[4]  Zheng Chen,et al.  CWS: a comparative web search system , 2006, WWW '06.

[5]  Olivia R. Liu Sheng,et al.  Designing a better web portal for digital government: a web-mining based approach , 2005, DG.O.

[6]  Janyce Wiebe,et al.  Effects of Adjective Orientation and Gradability on Sentence Subjectivity , 2000, COLING.

[7]  Marinos Themistocleous,et al.  Evaluating e‐government: learning from the experiences of two UK local authorities , 2005, Inf. Syst. J..

[8]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.

[9]  Carlo Strapparava,et al.  Unsupervised and supervised exploitation of semantic domains in lexical disambiguation , 2004, Comput. Speech Lang..

[10]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[11]  Janyce Wiebe,et al.  Learning Subjective Adjectives from Corpora , 2000, AAAI/IAAI.

[12]  Janyce Wiebe,et al.  Learning Subjective Language , 2004, CL.

[13]  Ryoji Kataoka,et al.  Opinion Sentence Search Engine on Open-Domain Blog , 2007, IJCAI.

[14]  Vasileios Hatzivassiloglou,et al.  Predicting the Semantic Orientation of Adjectives , 1997, ACL.

[15]  Dan Jurafsky,et al.  Automatic Extraction of Opinion Propositions and their Holders , 2004 .

[16]  Stefan Böttcher,et al.  Building Semantic Webs for e-government with Wiki technology , 2006, Electron. Gov. an Int. J..

[17]  Claire Cardie,et al.  Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns , 2005, HLT.

[18]  Jo Steyaert,et al.  Local Governments Online and the Role of the Resident , 2000 .

[19]  A. Whyte.  EVALUATING HOW EPARTICIPATION CHANGES LOCAL DEMOCRACY , 2006 .

[20]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[21]  Giovanni Maria Sacco.  User-Centric Access to e-Government Information: e-Citizen Discovery of e-Services , 2006, AAAI Spring Symposium: Semantic Web Meets eGovernment.

[22]  David E. Culler,et al.  Scalable, distributed data structures for internet service construction , 2000, OSDI.

[23]  Peter D. Turney.  Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews , 2002, ACL.

[24]  David Osimo.  Benchmarking eGovernment in the Web 2.0 era: what to measure, and how , 2008 .

[25]  Hsin-Hsi Chen,et al.  Mining opinions from the Web: Beyond relevance retrieval , 2007, J. Assoc. Inf. Sci. Technol..