Texts propagate through many social networks and provide evidence for their structure. We describe and evaluate efficient algorithms for detecting clusters of reused passages embedded within longer documents in large collections. We apply these techniques to two case studies: analyzing the culture of free reprinting in the nineteenth-century United States and the development of bills into legislation in the U.S. Congress. Using these divergent case studies, we evaluate both the efficiency of the approximate local text reuse detection methods and the accuracy of the results. These techniques allow us to explore how ideas spread, which ideas spread, and which subgroups shared ideas.
Description
Detecting and modeling local text reuse | IEEE Conference Publication | IEEE Xplore
%0 Conference Paper
%1 smith2014detecting
%A Smith, David A.
%A Cordel, Ryan
%A Dillon, Elizabeth Maddock
%A Stramp, Nick
%A Wilkerson, John
%B Proceedings of the IEEE/ACM Joint Conference on Digital Libraries
%D 2014
%K algorithm citation detection dh method quotation reuse text
%P 183--192
%R 10.1109/JCDL.2014.6970166
%T Detecting and modeling local text reuse
%U https://ieeexplore.ieee.org/abstract/document/6970166
%X Texts propagate through many social networks and provide evidence for their structure. We describe and evaluate efficient algorithms for detecting clusters of reused passages embedded within longer documents in large collections. We apply these techniques to two case studies: analyzing the culture of free reprinting in the nineteenth-century United States and the development of bills into legislation in the U.S. Congress. Using these divergent case studies, we evaluate both the efficiency of the approximate local text reuse detection methods and the accuracy of the results. These techniques allow us to explore how ideas spread, which ideas spread, and which subgroups shared ideas.
@inproceedings{smith2014detecting,
abstract = {Texts propagate through many social networks and provide evidence for their structure. We describe and evaluate efficient algorithms for detecting clusters of reused passages embedded within longer documents in large collections. We apply these techniques to two case studies: analyzing the culture of free reprinting in the nineteenth-century United States and the development of bills into legislation in the U.S. Congress. Using these divergent case studies, we evaluate both the efficiency of the approximate local text reuse detection methods and the accuracy of the results. These techniques allow us to explore how ideas spread, which ideas spread, and which subgroups shared ideas.},
added-at = {2022-05-10T20:39:28.000+0200},
author = {Smith, David A. and Cordel, Ryan and Dillon, Elizabeth Maddock and Stramp, Nick and Wilkerson, John},
biburl = {https://www.bibsonomy.org/bibtex/26f4cc266b5b58e4fbabb70b4b9ea36f0/jaeschke},
booktitle = {Proceedings of the IEEE/ACM Joint Conference on Digital Libraries},
description = {Detecting and modeling local text reuse | IEEE Conference Publication | IEEE Xplore},
doi = {10.1109/JCDL.2014.6970166},
interhash = {fc89d23e2f4bb4d3a34b2b5a191c243f},
intrahash = {6f4cc266b5b58e4fbabb70b4b9ea36f0},
keywords = {algorithm citation detection dh method quotation reuse text},
month = sep,
pages = {183--192},
series = {JCDL '14},
timestamp = {2022-05-10T20:39:28.000+0200},
title = {Detecting and modeling local text reuse},
url = {https://ieeexplore.ieee.org/abstract/document/6970166},
year = 2014
}