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

Abstract

Peer-review is the most common practice for accessing submitted papers.Previous research mainly focused on maximizing topic relevance and avoiding direct Conflict of Interest (COI) relationship between submitted authors of papers and reviewers.However, potential relationships of Conflict of Interests were not considered which might cause unfair in reviewing process.Hence, in this research, an approach of paper-reviewer assignment was proposed considering potential Conflict of Interests between authors of submitted papers and reviewers.First, academic networks of scholar-to-scholar and institution-to-institution were extracted from their academic activities records.Second, potential conflict of interests of papers-reviewers were measured utilizing paths distance between related authors and reviewers on in academic networks, topic relevance of papers-reviewers was measured using similarity between submitted papers content and publications of reviewers.Third, the paper-reviewer assignment approach was linked to a minimum cost maximum flow problem, which maximized topic relevance and minimized Conflict of Interests under the given constraints.With a big volume of real scholar data and a real task of conference paper-reviewer assignment, the proposed approach was evaluated.The experimental results validated the effectiveness of the proposed approach.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.