Visual Abstraction and Ordering in Faceted Browsing of Text Collections

Abstract

Faceted navigation is a technique for the exploration and discovery of a collection of resources, which can be of various types including text documents. While being information-rich resources, documents are usually not treated as content-bearing items in faceted browsing interfaces, and yet the required clean metadata is not always available or matches users' interest. In addition, the existing linear listing paradigm for representing result items from the faceted filtering process makes it difficult for users to traverse or compare across facet values in different orders of importance to them. In this context, we report in this article a visual support toward faceted browsing of a collection of documents based on a set of entities of interest to users. Our proposed approach involves using a multi-dimensional visualization as an alternative to the linear listing of focus items. In this visualization, visual abstraction based on a combination of a conceptual structure and the structural equivalence of documents can be simultaneously used to deal with a large number of items. Furthermore, the approach also enables visual ordering based on the importance of facet values to support prioritized, cross-facet comparisons of focus items. A user study was conducted and the results suggest that interfaces using the proposed approach can support users better in exploratory tasks and were also well-liked by the participants of the study, with the hybrid interface combining the multidimensional visualization with the linear listing receiving the most favorable ratings.Faceted browsing is a navigation technique for the exploration and discovery of a resource collection [Hearst 2008]. Apart from being studied in many research works such P.-Y. Rouille participated in this work during a research internship at DERI.