M. Valenzuela, V. Ha, and O. Etzioni. Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Papers from the 2015 AAAI Workshop, WS-15-13, page 21--26. Menlo Park, CA, AAAI Press, (2015)
Abstract
We introduce the novel task of identifying important citations in scholarly literature, i.e., citations that indicate that the cited work is used or extended in the new effort. We believe this task is a crucial component in algorithms that detect and follow research topics and in methods that measure the quality of publications.We model this task as a supervised classification problem at two levels of detail: a coarse one with classes (important vs. non-important), and a more detailed one with four importance classes. We annotate a dataset of approximately 450 citations with this information, and release it publicly. We propose a supervised classification approach that addresses this task with a battery of features that range from citation counts to where the citation appears in the body of the paper, and show that,our approach achieves a precision of 65 percent for a recall of 90 percent.
%0 Conference Paper
%1 ValenzuelaHaEtzioni15AAAI
%A Valenzuela, Marco
%A Ha, Vu
%A Etzioni, Oren
%B Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Papers from the 2015 AAAI Workshop
%C Menlo Park, CA
%D 2015
%E Caragea, Cornelia
%E Giles, C. Lee
%E Bhamidipati, Narayan
%E Caragea, Doina
%E Das Gollapalli, Sujatha
%E Kataria, Saurabh
%E Liu, Huan
%E Xia, Feng
%I AAAI Press
%K 01624 aaai paper ai conference language processing publications information retrieval semantic analysis search learn
%N WS-15-13
%P 21--26
%T Identifying Meaningful Citations
%U http://www.aaai.org/Library/Workshops/ws15-13.php
%X We introduce the novel task of identifying important citations in scholarly literature, i.e., citations that indicate that the cited work is used or extended in the new effort. We believe this task is a crucial component in algorithms that detect and follow research topics and in methods that measure the quality of publications.We model this task as a supervised classification problem at two levels of detail: a coarse one with classes (important vs. non-important), and a more detailed one with four importance classes. We annotate a dataset of approximately 450 citations with this information, and release it publicly. We propose a supervised classification approach that addresses this task with a battery of features that range from citation counts to where the citation appears in the body of the paper, and show that,our approach achieves a precision of 65 percent for a recall of 90 percent.
@inproceedings{ValenzuelaHaEtzioni15AAAI,
abstract = {We introduce the novel task of identifying important citations in scholarly literature, i.e., citations that indicate that the cited work is used or extended in the new effort. We believe this task is a crucial component in algorithms that detect and follow research topics and in methods that measure the quality of publications.We model this task as a supervised classification problem at two levels of detail: a coarse one with classes (important vs. non-important), and a more detailed one with four importance classes. We annotate a dataset of approximately 450 citations with this information, and release it publicly. We propose a supervised classification approach that addresses this task with a battery of features that range from citation counts to where the citation appears in the body of the paper, and show that,our approach achieves a precision of 65 percent for a recall of 90 percent.},
added-at = {2016-06-11T10:50:41.000+0200},
address = {Menlo Park, CA},
author = {Valenzuela, Marco and Ha, Vu and Etzioni, Oren},
biburl = {https://www.bibsonomy.org/bibtex/2ebd6bcb7436a6251c45a11263c30edce/flint63},
booktitle = {Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Papers from the 2015 AAAI Workshop},
crossref = {AAAI2015WS13},
editor = {Caragea, Cornelia and Giles, C. Lee and Bhamidipati, Narayan and Caragea, Doina and Das Gollapalli, Sujatha and Kataria, Saurabh and Liu, Huan and Xia, Feng},
file = {AAAI Digital Library:2015/ValenzuelaHaEtzioni15AAAI.pdf:PDF},
groups = {public},
interhash = {6fb4132fcf04a0d66b31ed98e858d9c5},
intrahash = {ebd6bcb7436a6251c45a11263c30edce},
keywords = {01624 aaai paper ai conference language processing publications information retrieval semantic analysis search learn},
number = {WS-15-13},
pages = {21--26},
publisher = {AAAI Press},
series = {Technical Report},
timestamp = {2017-07-13T18:16:28.000+0200},
title = {Identifying Meaningful Citations},
url = {http://www.aaai.org/Library/Workshops/ws15-13.php},
username = {flint63},
year = 2015
}