Clustering legal artifacts using text mining

The globalization of communication networks and the possibilities offered by the information and communication technologies (ICTs) significantly change the public sector's operation and services. Digital Governance is now integrated into administrations' policies and programs at all levels: local, regional, national, European. At the national level, there is a requirement to provide electronic public services according to citizens' needs while, in the sense of globalization, at the European level, there are many programs (e.g., the Europe 2005 and i2010 program) emphasizing the Digital Governance world (or better Digital Governance community) that indicates rapid changes not only in the sense of the change in the public sector's systems but also in the mentality that the public sector operates. On the other hand, Digital Governance's evolution affects societies intensively, emphasizing the importance of cross-border interaction and information sharing between them. [6]. Concerning the legal informatics domain, this can result in changing governments' operations in many ways [2]. By now, the massive amount of each country's legal information currently remains fragmented across multiple national databases and systems or even better legal databases. Most of these legal databases result from the significant advancements in the “legal informatics” research field that observed since governments have started to promote the development of legal information systems [9]. This research contributes to this purpose by developing an open and automated legal system capable of providing any EU country's legal information based on the existing ontologies.