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 McNamara

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

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. In 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 languageEnglish (US)
Title of host publicationProceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages566-570
Number of pages5
ISBN (Electronic)9781538618394
DOIs
StatePublished - Jul 5 2017
Event21st International Conference on Control Systems and Computer Science, CSCS 2017 - Bucharest
Duration: May 29 2017May 31 2017

Other

Other21st International Conference on Control Systems and Computer Science, CSCS 2017
CityBucharest
Period5/29/175/31/17

Fingerprint

Semantic Similarity
Semantics
Ranking
Social Network Analysis
Semantic Annotation
Overflow
Centrality
Eccentricity
Citations
Electric network analysis
Model
Metric
Methodology
Experiment
Experiments

Keywords

  • Co-authorship networks
  • Discourse analysis
  • Semantic similarity
  • Social network analysis

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Control and Optimization
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Paraschiv, I. C., Dascalu, M., Trausan-Matu, S., Nistor, N., Oca, A. M. M. D., & McNamara, D. (2017). Semantic Similarity versus Co-Authorship Networks: A Detailed Comparison. In Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017 (pp. 566-570). [7968614] Institute of Electrical and Electronics Engineers Inc.. 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; Oca, Ambar Murillo Montes De; McNamara, Danielle.

Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 566-570 7968614.

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

Paraschiv, IC, Dascalu, M, Trausan-Matu, S, Nistor, N, Oca, AMMD & McNamara, D 2017, Semantic Similarity versus Co-Authorship Networks: A Detailed Comparison. in Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017., 7968614, Institute of Electrical and Electronics Engineers Inc., pp. 566-570, 21st International Conference on Control Systems and Computer Science, CSCS 2017, Bucharest, 5/29/17. https://doi.org/10.1109/CSCS.2017.86
Paraschiv IC, Dascalu M, Trausan-Matu S, Nistor N, Oca AMMD, McNamara D. Semantic Similarity versus Co-Authorship Networks: A Detailed Comparison. In Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 566-570. 7968614 https://doi.org/10.1109/CSCS.2017.86
Paraschiv, Ionut Cristian ; Dascalu, Mihai ; Trausan-Matu, Stefan ; Nistor, Nicolae ; Oca, Ambar Murillo Montes De ; McNamara, Danielle. / Semantic Similarity versus Co-Authorship Networks : A Detailed Comparison. Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 566-570
@inproceedings{76939c8c12464163b7a2ea818c32feb1,
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. In 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 = "Co-authorship networks, Discourse analysis, Semantic similarity, Social network analysis",
author = "Paraschiv, {Ionut Cristian} and Mihai Dascalu and Stefan Trausan-Matu and Nicolae Nistor and Oca, {Ambar Murillo Montes De} and Danielle McNamara",
year = "2017",
month = "7",
day = "5",
doi = "10.1109/CSCS.2017.86",
language = "English (US)",
pages = "566--570",
booktitle = "Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Semantic Similarity versus Co-Authorship Networks

T2 - A Detailed Comparison

AU - Paraschiv, Ionut Cristian

AU - Dascalu, Mihai

AU - Trausan-Matu, Stefan

AU - Nistor, Nicolae

AU - Oca, Ambar Murillo Montes De

AU - McNamara, Danielle

PY - 2017/7/5

Y1 - 2017/7/5

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. In 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. In 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 - Co-authorship networks

KW - Discourse analysis

KW - Semantic similarity

KW - Social network analysis

UR - http://www.scopus.com/inward/record.url?scp=85027529454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027529454&partnerID=8YFLogxK

U2 - 10.1109/CSCS.2017.86

DO - 10.1109/CSCS.2017.86

M3 - Conference contribution

SP - 566

EP - 570

BT - Proceedings - 2017 21st International Conference on Control Systems and Computer, CSCS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -