On combining text-based and link-based similarity measures for scientific papers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In computing the similarity of scientific papers, text-based and link-based similarity measures look at only a single side of the content or citations. In this paper, we propose a new approach to compute the similarity of scientific papers accurately by combining the text-based and link-based similarity measures. Our proposed method considers the content and citations of the scientific papers simultaneously and combines the similarity scores based on the content and citations by using SVMrank. The effectiveness of our proposed method is demonstrated via extensive experiments on a real-world dataset of scientific papers. The results show that more than 20% improvement in accuracy is obtained with our approach compared with previous methods.

Original languageEnglish
Title of host publicationProceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013
Pages111-115
Number of pages5
DOIs
StatePublished - 2013 Dec 1
Event2013 Research in Adaptive and Convergent Systems, RACS 2013 - Montreal, QC, Canada
Duration: 2013 Oct 12013 Oct 4

Publication series

NameProceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013

Other

Other2013 Research in Adaptive and Convergent Systems, RACS 2013
CountryCanada
CityMontreal, QC
Period13/10/113/10/4

Fingerprint

Experiments

Keywords

  • citation
  • content
  • scientific papers
  • similarity

Cite this

Hamedani, R., Lee, S. C., & Kim, S-W. (2013). On combining text-based and link-based similarity measures for scientific papers. In Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013 (pp. 111-115). (Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013). https://doi.org/10.1145/2513228.2513321
Hamedani, Reyhani ; Lee, Sang Chul ; Kim, Sang-Wook. / On combining text-based and link-based similarity measures for scientific papers. Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013. 2013. pp. 111-115 (Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013).
@inproceedings{82be257a9b6846f09d10dc4fa416c0e4,
title = "On combining text-based and link-based similarity measures for scientific papers",
abstract = "In computing the similarity of scientific papers, text-based and link-based similarity measures look at only a single side of the content or citations. In this paper, we propose a new approach to compute the similarity of scientific papers accurately by combining the text-based and link-based similarity measures. Our proposed method considers the content and citations of the scientific papers simultaneously and combines the similarity scores based on the content and citations by using SVMrank. The effectiveness of our proposed method is demonstrated via extensive experiments on a real-world dataset of scientific papers. The results show that more than 20{\%} improvement in accuracy is obtained with our approach compared with previous methods.",
keywords = "citation, content, scientific papers, similarity",
author = "Reyhani Hamedani and Lee, {Sang Chul} and Sang-Wook Kim",
year = "2013",
month = "12",
day = "1",
doi = "10.1145/2513228.2513321",
language = "English",
isbn = "9781450323482",
series = "Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013",
pages = "111--115",
booktitle = "Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013",

}

Hamedani, R, Lee, SC & Kim, S-W 2013, On combining text-based and link-based similarity measures for scientific papers. in Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013. Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013, pp. 111-115, 2013 Research in Adaptive and Convergent Systems, RACS 2013, Montreal, QC, Canada, 13/10/1. https://doi.org/10.1145/2513228.2513321

On combining text-based and link-based similarity measures for scientific papers. / Hamedani, Reyhani; Lee, Sang Chul; Kim, Sang-Wook.

Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013. 2013. p. 111-115 (Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - On combining text-based and link-based similarity measures for scientific papers

AU - Hamedani, Reyhani

AU - Lee, Sang Chul

AU - Kim, Sang-Wook

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In computing the similarity of scientific papers, text-based and link-based similarity measures look at only a single side of the content or citations. In this paper, we propose a new approach to compute the similarity of scientific papers accurately by combining the text-based and link-based similarity measures. Our proposed method considers the content and citations of the scientific papers simultaneously and combines the similarity scores based on the content and citations by using SVMrank. The effectiveness of our proposed method is demonstrated via extensive experiments on a real-world dataset of scientific papers. The results show that more than 20% improvement in accuracy is obtained with our approach compared with previous methods.

AB - In computing the similarity of scientific papers, text-based and link-based similarity measures look at only a single side of the content or citations. In this paper, we propose a new approach to compute the similarity of scientific papers accurately by combining the text-based and link-based similarity measures. Our proposed method considers the content and citations of the scientific papers simultaneously and combines the similarity scores based on the content and citations by using SVMrank. The effectiveness of our proposed method is demonstrated via extensive experiments on a real-world dataset of scientific papers. The results show that more than 20% improvement in accuracy is obtained with our approach compared with previous methods.

KW - citation

KW - content

KW - scientific papers

KW - similarity

UR - http://www.scopus.com/inward/record.url?scp=84891440692&partnerID=8YFLogxK

U2 - 10.1145/2513228.2513321

DO - 10.1145/2513228.2513321

M3 - Conference contribution

AN - SCOPUS:84891440692

SN - 9781450323482

T3 - Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013

SP - 111

EP - 115

BT - Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013

ER -

Hamedani R, Lee SC, Kim S-W. On combining text-based and link-based similarity measures for scientific papers. In Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013. 2013. p. 111-115. (Proceedings of the 2013 Research in Adaptive and Convergent Systems, RACS 2013). https://doi.org/10.1145/2513228.2513321