Reviewer recommendation problem in the research field usually refers to invite experts to comment on the quality of papers, proposals, etc. How to effectively and accurately recommend reviewers for the submitted papers and proposals is a meaningful and still tough task. At present, many unsupervised recommendation methods have been researched to solve this task. In this paper, a novel classification method named Word Mover’s Distance–Constructive Covering Algorithm (WMD–CCA, for short) is proposed to solve the reviewer recommendation problem as a classification issue. A submission or a reviewer is described by some tags, such as keywords, research interests, and so on. First, the submission or the reviewer is represented as some vectors by a word embedding method. That is to say, each tag describing a submission or a reviewer is represented as a vector. Second, the Word Mover’s Distance (WMD, for short) method is used to measure the minimum distances between submissions and reviewers. Actually, the papers usually have research field information, and utilizing them well might improve the reviewer recommendation accuracy. So finally, the reviewer recommendation task is transformed into a classification problem which is solved by a supervised learning method- Constructive Covering Algorithm (CCA, for short). Comparative experiments are conducted with 4 public datasets and a synthetic dataset from Baidu Scholar, which show that the proposed method WMD–CCA effectively solves the reviewer recommendation task as a classification issue and improves the recommendation accuracy.

A novel classification method for paper-reviewer recommendation

The paper-reviewer recommendation task is of significant academic importance for conference chairs and journal editors. It aims to recommend appropriate experts in a discipline to comment on the quality of papers of others in that discipline. How to effectively and accurately recommend reviewers for the submitted papers is a meaningful and still tough task. Generally, the relationship between a paper and a reviewer often depends on the semantic expressions of them. Creating a more expressive representation can make the peer-review process more robust and less arbitrary. So the representations of a paper and a reviewer are very important for the paper-reviewer recommendation. Actually, a reviewer or a paper often belongs to multiple research fields, which increases difficulty in paper-reviewer recommendation. In this article, we propose a Multi-Label Classification method using a HIErarchical and transPArent Representation named Hiepar-MLC. First, we introduce HIErarchical and transPArent Representation (Hiepar) to express the semantic information of the reviewer and the paper. Hiepar is learned from a two-level bidirectional gated recurrent unit based network applying the attention mechanism. It is capable of capturing the two-level hierarchical information (word-sentence-document) and highlighting the elements in reviewers or papers to support the labels. This word-sentence-document information mirrors the hierarchical structure of a reviewer or a paper and captures the exact semantics of them. Then we transform the paper-reviewer recommendation problem into a multi-level classification issue, whose multiple research labels exactly guide the learning process. It is flexible in that we can select any multi-label classification method to solve the paper-reviewer recommendation problem. Further, we propose a simple multi-label-based reviewer assignment (MLBRA) strategy to select the appropriate reviewers. It is interesting in that we also explore the paper-reviewer recommendation in the coarse-grain granularity. Extensive experiments on the real-world dataset consisting of the papers in the ACM Digital Library show that Hiepar-MLC achieves better label prediction performance than the existing representation alternatives. In addition, with the MLBRA strategy, we show the effectiveness and the feasibility of our transformation from paper-reviewer recommendation to multi-label classification.

A Multi-Label Classification Method Using a Hierarchical and Transparent Representation for Paper-Reviewer Recommendation

This paper investigates the moderating role of a host government that promotes a multi-sided platform (MSP) as an alternative supply chain finance (SCF) solution. The MSP comprises equity crowdfunding, fixed-income funds, and low-rate lending facilities. We examine the sequential interactions between the host government (as the dominant legislator), a crowd of risk-averse small investors, and two competing SCs (local and foreign) that are engaged in Cournot competition. The players’ equilibrium strategies are characterized under two platform power structures, namely small investors-led and SC-led. The joint impact of government legislation and platform’s configuration on the performance of the proposed SCF mechanism is investigated. Results reveal that, while the regulated MSP outperforms a deregulated scenario, the profit-seeking behavior of the host government may intensify the power struggle between the local SC and small investors, and restrict the platform’s overall performance. To successfully practice smart protectionism, policy makers are urged to reframe existing SCF schemes by leveraging their moderating influence and prioritizing social welfare over their short-term economic goals. This not only abates the power imbalance in MSPs, but also enhances the players’ participation and enables host governments to further support their digital platform economy in the era of reglobalization.

Reframing supply chain finance in an era of reglobalization: On the value of multi-sided crowdfunding platforms

https://link.springer.com/content/pdf/10.1007/s12525-022-00537-z.pdf

Artificial intelligence in E-Commerce: a bibliometric study and literature review

Interdisciplinary studies are becoming increasingly popular, and research domains of many experts are becoming diverse. This phenomenon brings difficulty in recommending experts to review interdisc...

Author–Subject–Topic model for reviewer recommendation:

Reviewer assignment problem in the research field usually refers to invite experts for comments on the quality of papers, projects, etc. Different factors in conventional approaches are reckoned to choose appropriate reviewers, such as the relevance between reviewer candidates and submissions, the diversity of candidates. However, many studies ignore the temporal changes of reviewer interest and the stability of reviewers' interest trend. Accordingly, in this research, three indispensable aspects are analyzed, including the relevance between reviewer candidates and submissions, the interest trend of candidates as well as the authority of candidates. Next, with extracted aspects, the reviewer assignment is formulated as an integer linear programming problem. Finally, categories of comparative experiments are conducted with two large datasets that are built from WANFANG and ArnetMiner, which shows the availability of the proposed approach in modeling the temporal changes of reviewers' research interest. Also, it demonstrates the effectiveness of the proposed approach for the reviewer assignment problem.

Integrating the Trend of Research Interest for Reviewer Assignment

In the regular work process of peer review, editors have to read and understand the entire set of submissions to choose appropriate reviewers. However, due to a large number of submissions, to select reviewers manually becomes error-prone and time-consuming. In this research, a framework that considers different indispensable aspects such as topical relevance, topical authority and research interest is presented and, an integer linear programming problem is formulated with practical considerations to recommend reviewers for a group of submissions. Specifically, the topical relevance and the topical authority are utilized to recommend relevant and accredited candidates in submission-related topics, while the research interest is to exam the willingness of candidates to review a submission. To evaluate the effectiveness of the proposed approach, categories of comparative experiments were conducted on two large scholarly datasets. Experimental results demonstrate that, compared with benchmark approaches, the proposed approach is capable to capture the research interest of reviewer candidates without a significant loss in different evaluation metrics. Our work can be helpful for editors to invite matching experts in peer review and highlight the necessity to uncover valuable information from big scholarly data for expert selection.

Qian Geng

Papers

Integrating the Trend of Research Interest for Reviewer Assignment

Author–Subject–Topic model for reviewer recommendation:

An integer linear programming model of reviewer assignment with research interest considerations

Cross-domain ontology construction and alignment from online customer product reviews

Utilizing Academic-Network-Based Conflict of Interests: for Paper Reviewer Assignment