On exploiting static and dynamically mined metadata for exploratory web searching |
| |
Authors: | Panagiotis Papadakos Nikos Armenatzoglou Stella Kopidaki Yannis Tzitzikas |
| |
Affiliation: | 1. Institute of Computer Science (ICS), Foundation for Research and Technology – Hellas (FORTH), Vassilika Vouton, 700 13, Heraklion, Crete, Greece 2. Computer Science Department, University of Crete, L. Knossou, 714 09, Heraklion, Crete, Greece
|
| |
Abstract: | Most Web Search Engines (WSEs) are appropriate for focalized search, i.e., they make the assumption that users can accurately
describe their information need using a small sequence of terms. However, as several user studies have shown, a high percentage
of search tasks are exploratory, and focalized search very commonly leads to inadequate interactions and poor results. This
paper proposes exploiting static and dynamically mined metadata for enriching web searching with exploration services. Online results clustering, which is a mining task of dynamic nature since it is based on query-dependent snippets, is useful for providing users with
overviews of the top results and thus allowing them to restrict their focus to the desired parts. On the other hand, the various
static metadata that are available to a search engine (e.g., domain, language, date, and filetype) are commonly exploited only through the
advanced (form-based) search facilities that some WSEs offer (and users rarely use). We propose an approach that combines
both kinds of metadata by adopting the interaction paradigm of dynamic taxonomies and faceted exploration, which allows the users
to restrict their focus gradually using both static and dynamically derived metadata. Special focus is given on the design
and analysis of incremental algorithms for speeding up the exploration process. The experimental evaluation over a real WSE
shows that this combination results to an effective, flexible, and efficient exploration experience. Finally, we report the
results of a user study indicating that this direction is promising in terms of user preference, satisfaction, and effort. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|