Clustering versus faceted categories for information exploration

The role of clustering and faceted categories to design interfaces for supporting information exploration is discussed. Clustering is fully automatable and can easily be applied to any text collection and is useful for clarifying vague queries. This method also works well for disambiguating ambiguous queries but lacks predictability and the difficulty of labeling the groups. Another method called hierarchical faceted categories (HFC) provides an advantage over the unpredictable results of clustering. The approach reduces mental work by promoting recognition over recall and logically suggesting. Both methods are used for search interfaces in domain-specific collections including e-commerce interfaces to provide a custom solution.