Semantic Similarity versus Co-authorship Networks: A Detailed Comparison

Ionut Cristian Paraschiv; Mihai Dascalu; Stefan Trausan-Matu; Nicolae Nistor; Ambar Murillo Montes de Oca; Danielle S. McNamara

doi:10.1109/CSCS.2017.86

Semantic Similarity versus Co-authorship Networks: A Detailed Comparison

Ionut Cristian Paraschiv, Mihai Dascalu, Stefan Trausan-Matu, Nicolae Nistor, Ambar Murillo Montes de Oca, Danielle S. McNamara

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Whether interested in personal work, in learning about trending topics, or in finding the structure of a specific domain, individuals' work of staying up-to-date has become more and more difficult due to the increasing information overflow. ln our previous work our focus has been to create a semantic annotation model accompanied by dedicated views to explore the semantic similarities between scientific articles. This paper focuses on applying our approach on a dataset of 519 project proposal abstracts, with the intention to bring value to the current indexation methodologies that rely primarily on co- citations and keyword matching. Our experiment uses various Social Network Analysis metrics to compare the rankings generated by two complementary models relying on semantic similarity and co-authorship networks. The two models are statistically different based on representative project associations, are significantly correlated in terms of project rankings by eccentricity and closeness centrality, and the semantic similarity network is denser.

Original language	English
Title of host publication	21st International Conference on Control Systems and Computer Science (CSCS)
Publisher	IEEE
ISBN (Electronic)	2379-0482
DOIs	https://doi.org/10.1109/CSCS.2017.86
Publication status	Published - 7 Jul 2017
Externally published	Yes
Event	21st Int. Conf. on Control Systems and Computer Science (CSCS21) - Bucharest, Romania Duration: 29 May 2017 → 31 May 2017 https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7963998 https://cscs21.hpc.pub.ro/

Conference

Conference	21st Int. Conf. on Control Systems and Computer Science (CSCS21)
Abbreviated title	CSCS21
Country	Romania
City	Bucharest
Period	29/05/17 → 31/05/17
Internet address	https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7963998 https://cscs21.hpc.pub.ro/

Keywords

semantic similarity
discourse analysis
co-authorship networks
social network analysis

Access to Document

10.1109/CSCS.2017.86

Fingerprint Dive into the research topics of 'Semantic Similarity versus Co-authorship Networks: A Detailed Comparison'. Together they form a unique fingerprint.

Projects

1 Finished

Rage: Realising an Applied Gaming Eco-system

Westera, W., Georgiadis, K., Saveski, G., van Lankveld, G., Bahreini, K., van der Vegt, W., Berkhout, J., Nyamsuren, E., Kluijfhout, E. & Nadolski, R.

1/02/15 → 31/07/19

Project: Research

Cite this

Paraschiv, I. C., Dascalu, M., Trausan-Matu, S., Nistor, N., Montes de Oca, A. M., & McNamara, D. S. (2017). Semantic Similarity versus Co-authorship Networks: A Detailed Comparison. In 21st International Conference on Control Systems and Computer Science (CSCS) IEEE. https://doi.org/10.1109/CSCS.2017.86

@inproceedings{2a35e540233e4132aa0739e4abb86153,

title = "Semantic Similarity versus Co-authorship Networks: A Detailed Comparison",

abstract = "Whether interested in personal work, in learning about trending topics, or in finding the structure of a specific domain, individuals' work of staying up-to-date has become more and more difficult due to the increasing information overflow. ln our previous work our focus has been to create a semantic annotation model accompanied by dedicated views to explore the semantic similarities between scientific articles. This paper focuses on applying our approach on a dataset of 519 project proposal abstracts, with the intention to bring value to the current indexation methodologies that rely primarily on co- citations and keyword matching. Our experiment uses various Social Network Analysis metrics to compare the rankings generated by two complementary models relying on semantic similarity and co-authorship networks. The two models are statistically different based on representative project associations, are significantly correlated in terms of project rankings by eccentricity and closeness centrality, and the semantic similarity network is denser.",

keywords = "semantic similarity, discourse analysis, co-authorship networks, social network analysis",

author = "Paraschiv, {Ionut Cristian} and Mihai Dascalu and Stefan Trausan-Matu and Nicolae Nistor and {Montes de Oca}, {Ambar Murillo} and McNamara, {Danielle S.}",

year = "2017",

month = jul,

day = "7",

doi = "10.1109/CSCS.2017.86",

language = "English",

booktitle = "21st International Conference on Control Systems and Computer Science (CSCS)",

publisher = "IEEE",

address = "United States",

note = "21st Int. Conf. on Control Systems and Computer Science (CSCS21), CSCS21 ; Conference date: 29-05-2017 Through 31-05-2017",

url = "https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7963998, https://cscs21.hpc.pub.ro/",

}

Paraschiv, IC, Dascalu, M, Trausan-Matu, S, Nistor, N, Montes de Oca, AM & McNamara, DS 2017, Semantic Similarity versus Co-authorship Networks: A Detailed Comparison. in 21st International Conference on Control Systems and Computer Science (CSCS). IEEE, 21st Int. Conf. on Control Systems and Computer Science (CSCS21), Bucharest, Romania, 29/05/17. https://doi.org/10.1109/CSCS.2017.86

Semantic Similarity versus Co-authorship Networks: A Detailed Comparison. / Paraschiv, Ionut Cristian; Dascalu, Mihai; Trausan-Matu, Stefan; Nistor, Nicolae; Montes de Oca, Ambar Murillo; McNamara, Danielle S.

21st International Conference on Control Systems and Computer Science (CSCS). IEEE, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Semantic Similarity versus Co-authorship Networks: A Detailed Comparison

AU - Paraschiv, Ionut Cristian

AU - Dascalu, Mihai

AU - Trausan-Matu, Stefan

AU - Nistor, Nicolae

AU - Montes de Oca, Ambar Murillo

AU - McNamara, Danielle S.

PY - 2017/7/7

Y1 - 2017/7/7

N2 - Whether interested in personal work, in learning about trending topics, or in finding the structure of a specific domain, individuals' work of staying up-to-date has become more and more difficult due to the increasing information overflow. ln our previous work our focus has been to create a semantic annotation model accompanied by dedicated views to explore the semantic similarities between scientific articles. This paper focuses on applying our approach on a dataset of 519 project proposal abstracts, with the intention to bring value to the current indexation methodologies that rely primarily on co- citations and keyword matching. Our experiment uses various Social Network Analysis metrics to compare the rankings generated by two complementary models relying on semantic similarity and co-authorship networks. The two models are statistically different based on representative project associations, are significantly correlated in terms of project rankings by eccentricity and closeness centrality, and the semantic similarity network is denser.

AB - Whether interested in personal work, in learning about trending topics, or in finding the structure of a specific domain, individuals' work of staying up-to-date has become more and more difficult due to the increasing information overflow. ln our previous work our focus has been to create a semantic annotation model accompanied by dedicated views to explore the semantic similarities between scientific articles. This paper focuses on applying our approach on a dataset of 519 project proposal abstracts, with the intention to bring value to the current indexation methodologies that rely primarily on co- citations and keyword matching. Our experiment uses various Social Network Analysis metrics to compare the rankings generated by two complementary models relying on semantic similarity and co-authorship networks. The two models are statistically different based on representative project associations, are significantly correlated in terms of project rankings by eccentricity and closeness centrality, and the semantic similarity network is denser.

KW - semantic similarity

KW - discourse analysis

KW - co-authorship networks

KW - social network analysis

U2 - 10.1109/CSCS.2017.86

DO - 10.1109/CSCS.2017.86

M3 - Conference article in proceeding

BT - 21st International Conference on Control Systems and Computer Science (CSCS)

PB - IEEE

T2 - 21st Int. Conf. on Control Systems and Computer Science (CSCS21)

Y2 - 29 May 2017 through 31 May 2017

ER -