Data harvesting, curation and fusion model to support public service recommendations for e-governments

This work reports on early results from CITADEL project that aims at creating an ecosystem of best practices, tools, and recommendations to transform Public Administrations with more efficient, inclusive and citizen-centric services. The goal of the recommendations is to support Governments to find out why citizens stop using public services, and use this information to re-adjust provision to bring these citizens back in. Furthermore, it will help identifying why citizens are not using a given public service (due to affordability, accessibility, lack of knowledge, embarrassment, lack of interest, etc.) and, where appropriate, use this information to make public services more attractive, so they start using the services. While recommender systems can enhance experiences by providing targeted information, the entry barriers in terms of data acquisition are very high, often limiting recommender solutions to closed systems of user/context models. The main focus of this work is to provide an architectural model that allows harvesting data from various sources, curating datasets that originate from a multitude of formats and fusing them into semantically enhanced data that contain key performance indicators for the utility of e-Government services. The output can be further processed by analytics and/or recommender engines to suggest public service improvement needs.