Mining collaboration opportunities to support Joined-Up Government

Governments strive to achieve improvements in delivering public services, developing and implementing public policies, responding to crisis situations, and optimizing the use of public resources, among others. Achieving such goals requires collaboration across different levels and functions of government, and across public and private sectors in a Joined-Up Government. Establishing such collaboration requires information on prospective participants including their goals, resources, processes and services. Such information is rarely available in structured forms e.g. in databases, but instead scattered over government portals, publications and other textual sources. This paper proposes the use of semantic text mining for extracting collaboration-related information (focusing on government collaboration) from unstructured data sources. The proposed solution applies natural language processing techniques supported by the relevant domain and process ontologies. It consists of three steps: 1) extracting process-related information from textual sources, 2) creating process ontology instances from extracted information and 3) mining shared and integrated processes based on process instances and the service goal hierarchy in the domain ontology. The paper describes the rationale of and approach adopted in this research, the progress achieved in implementing step 1, the challenges encountered and how we intend to address them in pursuing subsequent steps.