A sentiment augmented deep architecture to predict peer review outcomes

Tirthankar Ghosal; Rajeev Verma; Asif Ekbal; Pushpak Bhattacharyya

doi:10.1109/JCDL.2019.00096

A sentiment augmented deep architecture to predict peer review outcomes

Tirthankar Ghosal, Rajeev Verma, Asif Ekbal, Pushpak Bhattacharyya

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

17 Scopus citations

Abstract

Peer review texts reflect the overall impression of the reviewers towards a candidate research paper and by far are the most important? artifact used by editors and program chairs to determine the prospective inclusion of a manuscript in a given journal or a conference. Here in this work, we study how we could make use of the sentiment information embedded within peer review texts to help editors or program chairs to make better editorial decisions. We design an efficient deep neural architecture that takes into account: the paper, the corresponding reviews, and sentiment polarity of the reviews to predict the recommendation score of reviewers and well as to anticipate the final decision. Our results show that we achieve significant improvement over the baselines (~ 29% error reduction) proposed in a recently released dataset of peer reviews.

Original language	English
Title of host publication	Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019
Editors	Maria Bonn, Dan Wu, Stephen J. Downie, Alain Martaus
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	414-415
Number of pages	2
ISBN (Electronic)	9781728115474
DOIs	https://doi.org/10.1109/JCDL.2019.00096
State	Published - Jun 2019
Externally published	Yes
Event	19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019 - Urbana-Champaign, United States Duration: Jun 2 2019 → Jun 6 2019

Publication series

Name	Proceedings of the ACM/IEEE Joint Conference on Digital Libraries
Volume	2019-June
ISSN (Print)	1552-5996

Conference

Conference	19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019
Country/Territory	United States
City	Urbana-Champaign
Period	06/2/19 → 06/6/19

Funding

ACKNOWLEDGMENTS The first and second author gratefully acknowledges Visvesvaraya Ph.D. Scheme and YFRF under Ministry of Electronics and Information Technology (MeitY), Government of India for support. REFERENCES

Keywords

Deep neural network
Peer review
Review sentiment analysis

Access to Document

10.1109/JCDL.2019.00096

Cite this

Ghosal, T., Verma, R., Ekbal, A., & Bhattacharyya, P. (2019). A sentiment augmented deep architecture to predict peer review outcomes. In M. Bonn, D. Wu, S. J. Downie, & A. Martaus (Eds.), Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019 (pp. 414-415). Article 8791212 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries; Vol. 2019-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/JCDL.2019.00096

Ghosal, Tirthankar ; Verma, Rajeev ; Ekbal, Asif et al. / A sentiment augmented deep architecture to predict peer review outcomes. Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019. editor / Maria Bonn ; Dan Wu ; Stephen J. Downie ; Alain Martaus. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 414-415 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries).

@inproceedings{d55ebc95d8e9433d956bef34f4abd796,

title = "A sentiment augmented deep architecture to predict peer review outcomes",

abstract = "Peer review texts reflect the overall impression of the reviewers towards a candidate research paper and by far are the most important? artifact used by editors and program chairs to determine the prospective inclusion of a manuscript in a given journal or a conference. Here in this work, we study how we could make use of the sentiment information embedded within peer review texts to help editors or program chairs to make better editorial decisions. We design an efficient deep neural architecture that takes into account: the paper, the corresponding reviews, and sentiment polarity of the reviews to predict the recommendation score of reviewers and well as to anticipate the final decision. Our results show that we achieve significant improvement over the baselines (~ 29% error reduction) proposed in a recently released dataset of peer reviews.",

keywords = "Deep neural network, Peer review, Review sentiment analysis",

author = "Tirthankar Ghosal and Rajeev Verma and Asif Ekbal and Pushpak Bhattacharyya",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019 ; Conference date: 02-06-2019 Through 06-06-2019",

year = "2019",

month = jun,

doi = "10.1109/JCDL.2019.00096",

language = "English",

series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "414--415",

editor = "Maria Bonn and Dan Wu and Downie, {Stephen J.} and Alain Martaus",

booktitle = "Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019",

}

Ghosal, T, Verma, R, Ekbal, A & Bhattacharyya, P 2019, A sentiment augmented deep architecture to predict peer review outcomes. in M Bonn, D Wu, SJ Downie & A Martaus (eds), Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019., 8791212, Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, vol. 2019-June, Institute of Electrical and Electronics Engineers Inc., pp. 414-415, 19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019, Urbana-Champaign, United States, 06/2/19. https://doi.org/10.1109/JCDL.2019.00096

A sentiment augmented deep architecture to predict peer review outcomes. / Ghosal, Tirthankar; Verma, Rajeev; Ekbal, Asif et al.
Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019. ed. / Maria Bonn; Dan Wu; Stephen J. Downie; Alain Martaus. Institute of Electrical and Electronics Engineers Inc., 2019. p. 414-415 8791212 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries; Vol. 2019-June).

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

TY - GEN

T1 - A sentiment augmented deep architecture to predict peer review outcomes

AU - Ghosal, Tirthankar

AU - Verma, Rajeev

AU - Ekbal, Asif

AU - Bhattacharyya, Pushpak

PY - 2019/6

Y1 - 2019/6

N2 - Peer review texts reflect the overall impression of the reviewers towards a candidate research paper and by far are the most important? artifact used by editors and program chairs to determine the prospective inclusion of a manuscript in a given journal or a conference. Here in this work, we study how we could make use of the sentiment information embedded within peer review texts to help editors or program chairs to make better editorial decisions. We design an efficient deep neural architecture that takes into account: the paper, the corresponding reviews, and sentiment polarity of the reviews to predict the recommendation score of reviewers and well as to anticipate the final decision. Our results show that we achieve significant improvement over the baselines (~ 29% error reduction) proposed in a recently released dataset of peer reviews.

AB - Peer review texts reflect the overall impression of the reviewers towards a candidate research paper and by far are the most important? artifact used by editors and program chairs to determine the prospective inclusion of a manuscript in a given journal or a conference. Here in this work, we study how we could make use of the sentiment information embedded within peer review texts to help editors or program chairs to make better editorial decisions. We design an efficient deep neural architecture that takes into account: the paper, the corresponding reviews, and sentiment polarity of the reviews to predict the recommendation score of reviewers and well as to anticipate the final decision. Our results show that we achieve significant improvement over the baselines (~ 29% error reduction) proposed in a recently released dataset of peer reviews.

KW - Deep neural network

KW - Peer review

KW - Review sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=85070960650&partnerID=8YFLogxK

U2 - 10.1109/JCDL.2019.00096

DO - 10.1109/JCDL.2019.00096

M3 - Conference contribution

AN - SCOPUS:85070960650

T3 - Proceedings of the ACM/IEEE Joint Conference on Digital Libraries

SP - 414

EP - 415

BT - Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019

A2 - Bonn, Maria

A2 - Wu, Dan

A2 - Downie, Stephen J.

A2 - Martaus, Alain

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019

Y2 - 2 June 2019 through 6 June 2019

ER -

Ghosal T, Verma R, Ekbal A, Bhattacharyya P. A sentiment augmented deep architecture to predict peer review outcomes. In Bonn M, Wu D, Downie SJ, Martaus A, editors, Proceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 414-415. 8791212. (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries). doi: 10.1109/JCDL.2019.00096

A sentiment augmented deep architecture to predict peer review outcomes

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this