A robust model for paper-reviewer assignment

Xiang Liu, Torsten Suel, Nasir Memon

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

Abstract

Automatic expert assignment is a common problem encoun- tered in both industry and academia. For example, for conference program chairs and journal editors, in order to collect "good " judgments for a paper, it is necessary for them to assign the paper to the most appropriate reviewers. Choosing appropriate reviewers of course includes a number of considerations such as expertise and authority, but also diversity and avoiding con icts. In this paper, we explore the expert retrieval problem and implement an automatic paper-reviewer recommendation system that considers as- pects of expertise, authority, and diversity. In particular, a graph is first constructed on the possible reviewers and the query paper, incorporating expertise and authority in- formation. Then a Random Walk with Restart (RWR) [1] model is employed on the graph with a sparsity constraint, incorporating diversity information. Extensive experiments on two reviewer recommendation benchmark datasets show that the proposed method obtains performance gains over state-of-the-art reviewer recommendation systems in terms of expertise, authority, diversity, and, most importantly, rele- vance as judged by human experts.

Original languageEnglish (US)
Title of host publicationRecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages25-32
Number of pages8
ISBN (Print)9781450326681
DOIs
StatePublished - Oct 6 2014
Event8th ACM Conference on Recommender Systems, RecSys 2014 - Foster City, United States
Duration: Oct 6 2014Oct 10 2014

Other

Other8th ACM Conference on Recommender Systems, RecSys 2014
CountryUnited States
CityFoster City
Period10/6/1410/10/14

Fingerprint

Recommender systems
Industry
Experiments

Keywords

  • Diversity
  • Expert retrieval
  • Information propaga-tion
  • Random walk
  • Ranking
  • Review assignment
  • Topic model

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Liu, X., Suel, T., & Memon, N. (2014). A robust model for paper-reviewer assignment. In RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems (pp. 25-32). Association for Computing Machinery, Inc. https://doi.org/10.1145/2645710.2645749

A robust model for paper-reviewer assignment. / Liu, Xiang; Suel, Torsten; Memon, Nasir.

RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2014. p. 25-32.

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

Liu, X, Suel, T & Memon, N 2014, A robust model for paper-reviewer assignment. in RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, pp. 25-32, 8th ACM Conference on Recommender Systems, RecSys 2014, Foster City, United States, 10/6/14. https://doi.org/10.1145/2645710.2645749
Liu X, Suel T, Memon N. A robust model for paper-reviewer assignment. In RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2014. p. 25-32 https://doi.org/10.1145/2645710.2645749
Liu, Xiang ; Suel, Torsten ; Memon, Nasir. / A robust model for paper-reviewer assignment. RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2014. pp. 25-32
@inproceedings{b1dbe0dbd2394192a2124f7256ee632e,
title = "A robust model for paper-reviewer assignment",
abstract = "Automatic expert assignment is a common problem encoun- tered in both industry and academia. For example, for conference program chairs and journal editors, in order to collect {"}good {"} judgments for a paper, it is necessary for them to assign the paper to the most appropriate reviewers. Choosing appropriate reviewers of course includes a number of considerations such as expertise and authority, but also diversity and avoiding con icts. In this paper, we explore the expert retrieval problem and implement an automatic paper-reviewer recommendation system that considers as- pects of expertise, authority, and diversity. In particular, a graph is first constructed on the possible reviewers and the query paper, incorporating expertise and authority in- formation. Then a Random Walk with Restart (RWR) [1] model is employed on the graph with a sparsity constraint, incorporating diversity information. Extensive experiments on two reviewer recommendation benchmark datasets show that the proposed method obtains performance gains over state-of-the-art reviewer recommendation systems in terms of expertise, authority, diversity, and, most importantly, rele- vance as judged by human experts.",
keywords = "Diversity, Expert retrieval, Information propaga-tion, Random walk, Ranking, Review assignment, Topic model",
author = "Xiang Liu and Torsten Suel and Nasir Memon",
year = "2014",
month = "10",
day = "6",
doi = "10.1145/2645710.2645749",
language = "English (US)",
isbn = "9781450326681",
pages = "25--32",
booktitle = "RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - A robust model for paper-reviewer assignment

AU - Liu, Xiang

AU - Suel, Torsten

AU - Memon, Nasir

PY - 2014/10/6

Y1 - 2014/10/6

N2 - Automatic expert assignment is a common problem encoun- tered in both industry and academia. For example, for conference program chairs and journal editors, in order to collect "good " judgments for a paper, it is necessary for them to assign the paper to the most appropriate reviewers. Choosing appropriate reviewers of course includes a number of considerations such as expertise and authority, but also diversity and avoiding con icts. In this paper, we explore the expert retrieval problem and implement an automatic paper-reviewer recommendation system that considers as- pects of expertise, authority, and diversity. In particular, a graph is first constructed on the possible reviewers and the query paper, incorporating expertise and authority in- formation. Then a Random Walk with Restart (RWR) [1] model is employed on the graph with a sparsity constraint, incorporating diversity information. Extensive experiments on two reviewer recommendation benchmark datasets show that the proposed method obtains performance gains over state-of-the-art reviewer recommendation systems in terms of expertise, authority, diversity, and, most importantly, rele- vance as judged by human experts.

AB - Automatic expert assignment is a common problem encoun- tered in both industry and academia. For example, for conference program chairs and journal editors, in order to collect "good " judgments for a paper, it is necessary for them to assign the paper to the most appropriate reviewers. Choosing appropriate reviewers of course includes a number of considerations such as expertise and authority, but also diversity and avoiding con icts. In this paper, we explore the expert retrieval problem and implement an automatic paper-reviewer recommendation system that considers as- pects of expertise, authority, and diversity. In particular, a graph is first constructed on the possible reviewers and the query paper, incorporating expertise and authority in- formation. Then a Random Walk with Restart (RWR) [1] model is employed on the graph with a sparsity constraint, incorporating diversity information. Extensive experiments on two reviewer recommendation benchmark datasets show that the proposed method obtains performance gains over state-of-the-art reviewer recommendation systems in terms of expertise, authority, diversity, and, most importantly, rele- vance as judged by human experts.

KW - Diversity

KW - Expert retrieval

KW - Information propaga-tion

KW - Random walk

KW - Ranking

KW - Review assignment

KW - Topic model

UR - http://www.scopus.com/inward/record.url?scp=84908881619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908881619&partnerID=8YFLogxK

U2 - 10.1145/2645710.2645749

DO - 10.1145/2645710.2645749

M3 - Conference contribution

AN - SCOPUS:84908881619

SN - 9781450326681

SP - 25

EP - 32

BT - RecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

ER -