@inproceedings{d19e4e8a58a241f1988d626695ba442e,
title = "Classifying and ranking search engine results as potential sources of plagiarism",
abstract = "Source retrieval for plagiarism detection involves using a search engine to retrieve candidate sources of plagiarism for a given suspicious document so that more accurate comparisons can be made. An important consideration is that only documents that are likely to be sources of plagiarism should be retrieved so as to minimize the number of unnecessary comparisons made. A supervised strategy for source retrieval is described whereby search results are classified and ranked as potential sources of plagiarism without retrieving the search result documents and using only the information available at search time. The performance of the supervised method is compared to a baseline method and shown to improve precision by up to 3.28%, recall by up to 2.6% and the F1 score by up to 3.37%. Furthermore, features are analyzed to determine which of them are most important for search result classification with features based on document and search result similarity appearing to be the most important.",
keywords = "Plagiarism detection, Query generation, Search result ranking, Source retrieval",
author = "Kyle Williams and Chen, {Hung Hsuan} and Giles, {C. Lee}",
note = "Publisher Copyright: {\textcopyright} 2014 ACM.; 2014 ACM Symposium on Document Engineering, DocEng 2014 ; Conference date: 16-09-2014 Through 19-09-2014",
year = "2014",
doi = "10.1145/2644866.2644879",
language = "???core.languages.en_GB???",
series = "DocEng 2014 - Proceedings of the 2014 ACM Symposium on Document Engineering",
publisher = "Association for Computing Machinery, Inc",
pages = "97--106",
booktitle = "DocEng 2014 - Proceedings of the 2014 ACM Symposium on Document Engineering",
}