Formal Concept Analysis (FCA) is an unsupervised clustering technique and many scientific papers are devoted to applying FCA in Information Retrieval (IR) research. We collected 103 papers published between 2003-2009 which mention FCA and information retrieval in the abstract, title or keywords. Using a prototype of our FCA-based toolset CORDIET, we converted the pdf-files containing the papers to plain text, indexed them with Lucene using a thesaurus containing terms related to FCA research and then created the concept lattice shown in this paper. We visualized, analyzed and explored the literature with concept lattices and discovered multiple interesting research streams in IR of which we give an extensive overview. The core contributions of this paper are the innovative application of FCA to the text mining of scientific papers and the survey of the FCA-based IR research.

In this paper we introduce a novel human-centered data mining software system which was designed to gain intelligence from unstructured textual data. The architecture takes its roots in several case studies which were a collaboration between the Amsterdam-Amstelland Police, GasthuisZusters Antwerpen (GZA) hospitals and KU Leuven. It is currently being implemented by bachelor and master students of Moscow Higher School of Economics. At the core of the system are concept lattices which can be used to interactively explore the data. They are combined with several other complementary statistical data analysis techniques such as Emergent Self Organizing Maps and Hidden Markov Models.

This paper takes our research work with VDAB (Vlaamse Dienst voor Arbeidsbemiddeling en Beroepsopleiding), the public employment service for the Flemish region in Belgium, as a starting point to study the transformation of government from New Public Management (NPM) to Digital Era Governance (DEG). This study focuses on how to work towards disruptive DEG innovation in a turbulent strategic context by employing a strategy of simple rules. Together with VDAB we apply an Action Design Research (ADR) approach to develop a set of “boundary breaking rules”. Coining these simple rules represents a first significant step in VDAB’s journey towards achieving a radical business innovation. In addition to the main artifact designed using our ADR approach in the VDAB context, i.e. the “boundary breaking rules”, we derive lessons from this approach concerning the nature of this artifact specific for the VDAB case. Although this paper represents an early stage of the research and has not yet reached the final ADR stage of formalization of learning, we aim for it to lay the foundations for a more broadly applicable design theory of simple rules, useful in contexts generalizable from the specific VDAB context.

Smart city is a label internationally used by cities, researchers and technology providers with different meanings. As a popular concept it is widely used by city administrators and politicians to promote their efforts. It is hard enough to find a good definition for smart cities, but even harder to find a trustworthy description of what it takes to become a smart city and how a city administration is impacted. This paper sets out to investigate how a city, aspiring to become a 'smart city', can manage the organization to realize that ambition. Specifically, the paper describes the case of the City of Ghent, Belgium, and the key challenges it has been facing in its ongoing efforts to be a smart city. Based on in depth interviews with city representatives six key challenges for smart city realization were identified and tested with a panel of representatives from five European cities that are in the process of becoming a smart city. This way, the study contributes to a more professional pursuit of the smart city concept.

The topic of recommender systems is rapidly gaining interest in the user-behaviour modeling research domain. Over the years, various recommender algorithms based on different mathematical models have been introduced in the literature. Researchers interested in proposing a new recommender model or modifying an existing algorithm should take into account a variety of key performance indicators, such as execution time, recall and precision. Till date and to the best of our knowledge, no general cross-validation scheme to evaluate the performance of recommender algorithms has been developed. To fill this gap we propose an extension of conventional cross-validation. Besides splitting the initial data into training and test subsets, we also split the attribute description of the dataset into a hidden and visible part. We then discuss how such a splitting scheme can be applied in practice. Empirical validation is performed on traditional user-based and item-based recommender algorithms which were applied to the MovieLens dataset.