Interesting event detection through hall of fame rankings

Abstract

Everything is relative. Cars are compared by gas per mile, websites by page rank, students based on GPA, scientists by number of publications, and celebrities by beauty or wealth. In this paper, we study the characteristics of such entity rankings based on a set of rankings obtained from a popular Web portal. The obtained insights are integrated in our approach, coined Pantheon. Pantheon maintains sets of top-k rankings and reports identified changes in a way that appeals to users, using a novel combination of different characteristics like competitiveness, information entropy, and scale of change. Entity rankings are assembled by combining entity type attributes with data-driven categorical constraints and sorting criteria on numeric attributes. We report on the results of an experimental evaluation using real-world data obtained from a basketball statistics website.