| Abstract Detail
Systematics Section / ASPT Tang, Xiaoya [1], Heidorn, P. Bryan [2]. Using Automatically Generated Morphological Information in Botanical Text Retrieval. Users searching botanical texts in online and full-text indexes such as Google must accurately guess the vocabulary of the original authors to correctly match the words used in the text. However, although a large number of botanical volumes are available electronically, current retrieval systems on these collections are not able to interpret the specific information requests correctly and match them with appropriate documents. This study integrates text mining techniques into the botanical text retrieval process and automatically identifies selected plant morphological information from text to assist keyword-based retrieval. With this approach, users are able to search for documents about a plant by defining a set of plant characteristics using terms selected from a computer generated list. An experiment involving real users was conducted to evaluate this approach on the full-text botanical collection Flora of North America (FNA). The experimental results indicate that this approach improves keyword-based retrieval performance by allowing the users to complete more information tasks successfully than when people had to generate their own search terms. It also increases users’ satisfaction with the retrieval system.
Log in to add this item to your schedule
1 - Emporia State University, School of Library and Information Management, 1200 Commercial St., Campus Box 4025, Emporia, KS, 66801, USA
2 - University of Illinois at Urbana-Champaign, Graduate School of Library and Information Science, 501 East Daniel St. MC-493, Champaign, Illinois, 61820-6212, USA
Keywords:
Botanical Information
Retrieval.
Presentation Type: Oral Paper:Papers for Sections
Session: CP19
Location: PDR 2/Hilton
Date: Monday, July 9th, 2007
Time: 2:30 PM
Number: CP19006
Abstract ID:949 |
