We compare standard global IR searching with user-centric localized techniques to address the database selection problem. We conduct a series of experiments to compare the retrieval effectiveness of three separate search modes applied to a hierarchically structured data environment of textual database representations. The data environment is represented as a tree-like directory containing over 15,000 unique databases and over 100,000 total leaf nodes. Our search modes consist of varying degrees of browse and search, from a global search at the root node to a refined search at a sub-node using dynamically-calculated inverse document frequencies (idfs) to score candidate databases for probable relevance. Our findings indicate that a browse and search approach that relies upon localized searching from sub-nodes is capable of producing the most effective results.
[1]
Paul Thompson,et al.
TREC-3 Ad Hoc Retrieval and Routing Experiments using the WIN System
,
1994,
TREC.
[2]
Clement T. Yu,et al.
Concept hierarchy based text database categorization in a metasearch engine environment
,
2000,
Proceedings of the First International Conference on Web Information Systems Engineering.
[3]
James Allan,et al.
INQUERY Does Battle With TREC-6
,
1997,
TREC.
[4]
Soyeon Park.
Usability, user preferences, effectiveness, and user behaviors when searching individual and integrated full-text databases: implications for digital libraries
,
2000
.