Journal
2019 SIXTH INTERNATIONAL CONFERENCE ON SOCIAL NETWORKS ANALYSIS, MANAGEMENT AND SECURITY (SNAMS)
Volume -, Issue -, Pages 91-98Publisher
IEEE
Keywords
Conflict of Interests (CoIs); Knowledge Representation; Linked Open Data (LOD); SPARQL; DBLP; OWL; RDF; Latent Dirichlet Allocation (LDA); Apache Jena Fuseki
Funding
- Jordan University of Science and Technology [20170107]
Ask authors/readers for more resources
Scholarly peer review is a process of evaluating the suitability of a research work for publication judged by qualified researchers. A professional peer review process ensures the quality of the produced scientific research work. However, there are two main challenges to achieve professional peer review: (1) selecting reviewers with similar competences as the authors (peers) of a submitted research work and (2) resolving any Conflict of Interest (CoI) between reviewers and authors. Currently, to solve the first challenge, editors and conferences organizers select reviewers manually. Similarly, the current solution of the second challenge is that authors and reviewers are asked to manually declare any CoI. Such a manual solution is error-prone, waste time, and tedious for reviewers, authors, editors, and organizers. To address the aforementioned two challenges, we have developed a novel recommender system that (1) suggests expert reviewers and (2) resolves any CoI between the recommended reviewers and the author(s) of a submitted paper. To develop our recommender system, we utilized the DBLP citation network database represented as Linked Open Data. To select candidate reviewers who are expert in the topic of a submitted paper without CoIs, we use Latent Dirichlet Allocation (LDA) topic modeling to extract the topics researchers are working on and the topics of a submitted paper, then our system executes a SPARQL query that returns the best candidate reviewers. Finally, our system executes another SPARQL query that detects any CoIs between the candidate reviewers and the authors of a submitted paper and hence excludes them. Our experimental evaluations corroborate the ability or our system to recommend expert reviewers without CoIs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available