Improved reviewer assignment based on both word and semantic features

Tan, Shicheng; Duan, Zhenhai; Zhao, Shu; Chen, Jie; Zhang, Yanping

doi:10.1007/s10791-021-09390-8

Cited by 14 publications

(12 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some scholars have advocated combining word and semantic information to find the most qualified reviewers for a targeted proposal. To obtain a more accurate similarity score between reviewers and proposals, , Tang et al (2012) and Tan et al (2021) used both the LDA model and SLM. Similarly, in the wellknown reviewer assignment system TPMS, Charlin, and Zemel (2013) modeled the proposals and reviewers' published publications using the SLM and LDA.…”

Section: Methods Combining Word and Semantic Informationmentioning

confidence: 99%

“…The system needs to be automatic for more fair, objective, and expedient review assignments. Despite this requirement, the number of empirical studies submitted to the RAP for journal papers (Biswas & Hasan, 2007;Karimzadehgan & Zhai, 2009;Daud et al, 2010;Andrade-Navarro et al, 2012;Wang et al, 2013;Protasiewicz, 2014;Yin et al, 2016;Peng et al, 2017;Jin et al, 2018aJin et al, , 2018bZhao et al, 2018;Duan et al, 2019;Chughtai et al, 2019;Tan et al, 2021;Hoang et al, 2021) is less than that for conference papers.…”

Section: Rap For Journal Papersmentioning

confidence: 99%

“…In this section, text-based/content-based approaches are divided into two classes according to the different types of information used, inspired by Tan et al (2021): the word-based methods and the semantic-based methods. Although studies that focus on semantic-based and word-based methods alone are in the majority, some studies handled both semantic-based and word-based methods simultaneously.…”

Section: Text-based/content-based Approachesmentioning

confidence: 99%

“…The model captures the interchangeability of both words and texts with the Dirichlet distribution, allowing for a cohesive test data generation procedure. It is seen that LDA is widely applied to extract topics representation from the reviewer's published studies and the submitted proposals (Mimno & Mccallum, 2007;Tang et al, 2010;Tang et al, 2012;Charlin & Zemel, 2013;Liu et al, 2014;Xu & Zuo, 2016;Peng et al, 2017;Yan et al, 2017;Nguyen et al, 2018;Medakene et al, 2019;Pradhan et al, 2020;Yang et al, 2020;Patil & Mahalle, 2021;Tan et al, 2021;Hoang et al, 2021).…”

Section: Probabilistic Latent Semantic Analysis (Plsa)mentioning

confidence: 99%

See 3 more Smart Citations

Reviewer Assignment Problem: A Systematic Review of the Literature

Meltem¹,

Yanık

Amasyalı

2023

jair

View full text Add to dashboard Cite

Appropriate reviewer assignment significantly impacts the quality of proposal evaluation, as accurate and fair reviews are contingent on their assignment to relevant reviewers. The crucial task of assigning reviewers to submitted proposals is the starting point of the review process and is also known as the reviewer assignment problem (RAP). Due to the obvious restrictions of manual assignment, journal editors, conference organizers, and grant managers demand automatic reviewer assignment approaches. Many studies have proposed assignment solutions in response to the demand for automated procedures since 1992. The primary objective of this survey paper is to provide scholars and practitioners with a comprehensive overview of available research on the RAP. To achieve this goal, this article presents an in-depth systematic review of 103 publications in the field of reviewer assignment published in the past three decades and available in the Web of Science, Scopus, ScienceDirect, Google Scholar, and Semantic Scholar databases. This review paper classified and discussed the RAP approaches into two broad categories and numerous subcategories based on their underlying techniques. Furthermore, potential future research directions for each category are presented. This survey shows that the research on the RAP is becoming more significant and that more effort is required to develop new approaches and a framework.

show abstract

Section: Methods Combining Word and Semantic Informationmentioning

confidence: 99%

Section: Rap For Journal Papersmentioning

confidence: 99%

Section: Text-based/content-based Approachesmentioning

confidence: 99%

Section: Probabilistic Latent Semantic Analysis (Plsa)mentioning

confidence: 99%

See 2 more Smart Citations

Reviewer Assignment Problem: A Systematic Review of the Literature

Meltem¹,

Yanık

Amasyalı

2023

jair

View full text Add to dashboard Cite

show abstract

“…In another study, [38] demonstrated that LM smoothing plays an important role in improving collaborative filtering. [39] proposed an improved language model and topic model based on terms and semantics to assign (recommend) manuscripts to reviewers. Additionally, the IR-based recommendation is discussed in [40,41].…”

Section: Retrieval-based Recommendationmentioning

confidence: 99%

Semantic-aware Retrieval and Recommendation based on the Dirichlet Compound Language Model

Bahrani

Roelleke

2022

Preprint

View full text Add to dashboard Cite

Traditional bag-of-word Information Retrieval (IR) has led to quasi-standard models (e.g. TF-IDF, BM25) that are applied in the context of recommendation. While the benefits of semantic-aware models are clear, there is no standard semantic IR model, and this prevents the usage of semantic retrieval for tasks such as recommendation. We propose a ranking framework by quantifying parameters of the Dirichlet Compound Model (DCM) and using query performance prediction to aggregate scores of semantic extensions of DCM. Instead of employing heuristics, we introduce reasonable aggregation standards which are expandable to the recommendation task by considering user interaction (e.g. rating) as a semantic event. This approach helps to bridge the gap between advanced IR and recommendation. One of the main findings of this paper is that the concept-based extension of DCM consistently outweighed both terms-only and concept-only baselines concerning biomedical data. The DCM-based recommender system is also shown to be effective when applied on MovieLens, Book Crossing and LastFM. By bringing together recommendation (prediction) and retrieval, we lay the grounds for generalizable and hybrid algorithms. This paper shows how advanced but well-established probability distributions can be transparently leveraged in the standardization of semantic ranking methods, especially for applications in which recommendation (notification) is critical.

show abstract

Expertise Computation for Automatic Reviewer Assignment

Kwatra

Bhatnagar

2022

Information Integration and Web Intelligence

View full text Add to dashboard Cite

Improved reviewer assignment based on both word and semantic features

Cited by 14 publications

References 42 publications

Reviewer Assignment Problem: A Systematic Review of the Literature

Reviewer Assignment Problem: A Systematic Review of the Literature

Semantic-aware Retrieval and Recommendation based on the Dirichlet Compound Language Model

Expertise Computation for Automatic Reviewer Assignment

Contact Info

Product

Resources

About