Result diversification has recently attracted much attention as a means of increasing user satisfaction in recommendation systems and web search. In this work, we focus on achieving content diversity in the case of continuous data delivery, such as in the context of publish/subscribe systems. We define sliding-window diversity and present a suite of heuristics for its efficient computation alon...

While being it extremely important, many Exploratory Data Analysis (EDA [21]) systems have the inhability to perform classification and visualization in a continuous basis or to self-organize new data-items into the older ones (evenmore into new labels if necessary), which can be crucial in KDD Knowledge Discovery [10,1], Retrieval and Data Mining Systems [15,10] (interactive and online forms o...