An Interpretable Soft-Sensor Framework for Dissertation Peer Review Using BERT
Open Access
Abstract
Graduate education has entered the era of big data, and systematic analysis of dissertation evaluations has become crucial for quality monitoring. However, the complexity and subjectivity inherent in peer-review texts pose significant challenges for automated analysis. While natural language processing (NLP) offers potential solutions, most existing methods fail to adequately capture nuanced disciplinary criteria or provide interpretable inferences for educators. Inspired by soft-sensor, this study employs a BERT-based model enhanced with additional attention mechanisms to quantify latent evaluation dimensions from dissertation reviews. The framework integrates Shapley Additive exPlanations (SHAP) to ensure the interpretability of model predictions, combining deep semantic modeling with SHAP to quantify characteristic importance in academic evaluation. The experimental results demonstrate that the implemented model outperforms baseline methods in accuracy, precision, recall, and F1-score. Furthermore, its interpretability mechanism reveals key evaluation dimensions experts prioritize during the paper assessment. This analytical framework establishes an interpretable soft-sensor paradigm that bridges NLP with substantive review principles, providing actionable insights for enhancing dissertation improvement strategies.Keywords
Funding Information
- National Natural Science Foundation of China (62277010)
- Fujian-Xiamen-Qian’an National Independent Innovation Demonstration Zone (2022FX6)
This publication has 22 references indexed in Scilit:
- Enhancing peer review skills in higher education: a mixed-methods study on challenges and training needsDiscover Education, 2025
- Natural language processing in educational research: The evolution of research topicsEducation and Information Technologies, 2024
- Use of artificial intelligence and the future of peer reviewHealth Affairs Scholar, 2024
- Study on Chinese Semantic Entity Recognition Method for Cabin Utilizing BERT-BiGRU ModelIEEE Access, 2024
- Text Sentiment Analysis of Douban Film Short Comments Based on BERT-CNN-BiLSTM-Att ModelIEEE Access, 2024
- Artificial intelligence to support publishing and peer review: A summary and reviewLearned Publishing, 2023
- GeoTPE: A neural network model for geographical topic phrases extraction from literature based on BERT enhanced with relative position embeddingExpert Systems with Applications, 2023
- An enhanced guided LDA model augmented with BERT based semantic strength for aspect term extraction in sentiment analysisKnowledge-Based Systems, 2022
- A Primer on Neural Network Models for Natural Language ProcessingJournal of Artificial Intelligence Research, 2016
- The Global Burden of Journal Peer Review in the Biomedical Literature: Strong Imbalance in the Collective EnterprisePLOS ONE, 2016