Robust Document Clustering by Exploiting Feature Diversity in Cluster Ensembles

The performance of document clustering systems is conditioned by the use of optimal text representations, which are not only difficult to determine beforehand, but also may vary from one clustering problem to another. This work presents an approach based on feature diversity and cluster ensembles as a first step towards building document clustering systems that behave robustly across different clustering problems. Experiments conducted on three binary clustering problems of increasing difficulty show that the proposed method is i) robust to near-optimal model order selection, and ii) able to detect constructive interactions between different document representations, thus being capable of yielding consensus clusterings superior to any of the individual clusterings available.