Evaluating the Impact of the Long-S upon 18th-Century Encyclopedia Britannica Automatic Subject Metadata Generation Results

• Published in: Information technology and libraries Vol. 39; no. 3; pp. 1 - 13
• Main Author: Grabus, Sam
• Format: Journal Article
• Language: English
• Published: Chicago American Library Association 01.09.2020
• Subjects: 18th century; 19th century; Algorithms; Character Recognition; Comparative Analysis; Comparative studies; Demonstration Programs; Digitization; Encyclopedias; Humanities; Indexing; Information professionals; Information Retrieval; Keywords; Knowledge; Library of Congress Subject Headings; Mathematics; Metadata; Personality; Semantics; Statistical Analysis; Subject heading schemes; Subject indexing; Vocabularies & taxonomies; Vocabulary
• ISSN: 0730-9295; 2163-5226
• DOI: 10.6017/ital.v39i3.12235

This research compares automatic subject metadata generation when the pre-1800s Long-S character is corrected to a standard < s >. The test environment includes entries from the third edition of the Encyclopedia Britannica, and the HIVE automatic subject indexing tool. A comparative study of metadata generated before and after correction of the Long-S demonstrated an average of 26.51 percent potentially relevant terms per entry omitted from results if the Long-S is not corrected. Results confirm that correcting the Long-S increases the availability of terms that can be used for creating quality metadata records. A relationship is also demonstrated between shorter entries and an increase in omitted terms when the Long-S is not corrected.