@inproceedings{c1066d88997b465bb105f1944ada788e,
title = "The feasibility of investing in manual correction of metadata for a large-scale digital library",
abstract = "Given a large-scale digital library that automatically crawls and parses PDF files to generate metadata for documents and authors, we estimate the number of person-hours required to correct a small portion of the metadata, in the hope that a large portion of users can benefit from these corrections. We obtain users requests by analyzing Cite-SeerX's log files from September 2009 to March 2013. We found that the distribution of users requests for search is highly imbalanced: most document search queries and author search queries concentrate on a small set of terms. As a result, even for a large-scale digital library, we estimate it is affordable to invest a few person-hours to check the correctness of a few metadata, and thus provide benefits to a good portion of document search and author search requests.",
keywords = "Digital Library, Human-Aided Metadata Generation, Metadata Correction, Practicability, User Experience, User Satisfaction",
author = "Chen, {Hung Hsuan} and Madian Khabsa and Giles, {C. Lee}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 14th IEEE/ACM Joint Conference on Digital Libraries, JCDL 2014 ; Conference date: 08-09-2014 Through 12-09-2014",
year = "2014",
month = dec,
day = "1",
doi = "10.1109/JCDL.2014.6970172",
language = "???core.languages.en_GB???",
series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "225--228",
booktitle = "2014 IEEE/ACM Joint Conference on Digital Libraries, JCDL 2014",
}