Hierarchical Interdisciplinary Topic Detection Model for Research Proposal Classification

TL;DR

This paper introduces a deep hierarchical transformer and graph neural network model to automatically detect interdisciplinary research proposal topics, improving reviewer assignment fairness and accuracy.

Contribution

The study presents a novel hierarchical transformer combined with GNNs for interdisciplinary topic detection, addressing limitations of manual labeling.

Findings

The model outperforms existing methods on real-world datasets.

Expert evaluations confirm the accuracy of detected interdisciplinary topics.

The approach enhances fairness in proposal-reviewer matching.

Abstract

The peer merit review of research proposals has been the major mechanism for deciding grant awards. However, research proposals have become increasingly interdisciplinary. It has been a longstanding challenge to assign interdisciplinary proposals to appropriate reviewers, so proposals are fairly evaluated. One of the critical steps in reviewer assignment is to generate accurate interdisciplinary topic labels for proposal-reviewer matching. Existing systems mainly collect topic labels manually generated by principal investigators. However, such human-reported labels can be non-accurate, incomplete, labor intensive, and time costly. What role can AI play in developing a fair and precise proposal reviewer assignment system? In this study, we collaborate with the National Science Foundation of China to address the task of automated interdisciplinary topic path detection. For this purpose, we develop a deep Hierarchical Interdisciplinary Research Proposal Classification Network (HIRPCN). Specifically, we first propose a hierarchical transformer to extract the textual semantic information of proposals. We then design an interdisciplinary graph and leverage GNNs for learning representations of each discipline in order to extract interdisciplinary knowledge. After extracting the semantic and interdisciplinary knowledge, we design a level-wise prediction component to fuse the two types of knowledge representations and detect interdisciplinary topic paths for each proposal. We conduct extensive experiments and expert evaluations on three real-world datasets to demonstrate the effectiveness of our proposed model.