Envisioning dynamic quantum clustering in information retrieval

Abstract

Dynamic Quantum Clustering is a recent clustering technique which makes use of Parzen window estimator to construct a potential function whose minima are related to the clusters to be found. The dynamic of the system is computed by means of the Schrödinger differential equation. In this paper, we apply this technique in the context of Information Retrieval to explore its performance in terms of the quality of clusters and the efficiency of the computation. In particular, we want to analyze the clusters produced by using datasets of relevant and non-relevant documents given a topic. © 2011 Springer-Verlag.