Argument Mining Driven Analysis of Peer-Reviews

• DOI: 10.1609/aaai.v35i6.16607
• Publication Date: 2022-09-08T18:45:08Z
• Authors: Michael Fromm; Evgeniy Faerman; Max Berrendorf; Siddharth Bhargava; Ruoxia Qi; Yao Zhang; Lukas Dennert; Sophia Selle; Yang Mao; Thomas Seidl
• Keywords: Argument (complex analysis); Identification; Process mining

Peer reviewing is a central process in modern research and essential for ensuring high quality reliability of published work. At the same time, it time-consuming increasing interest emerging fields often results review workload, especially senior researchers this area. How to cope with problem an open question vividly discussed across all major conferences. In work, we propose Argument Mining based approach assistance editors, meta-reviewers, reviewers. We demonstrate that decision field scientific publications driven by arguments automatic argument identification helpful various use-cases. One our findings used peer-review differ from other domains making transfer pre-trained models difficult. Therefore, provide community new dataset peer-reviews different computer science conferences annotated arguments. extensive empirical evaluation, show can be efficiently extract most relevant parts reviews, which are paramount publication decision. Also, remains interpretable, since extracted highlighted without detaching them their context.