Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach

arXiv cs.CL Papers

Summary

This paper investigates the distribution and evolution of aspect-level sentiments in multi-round peer reviews from Nature Communications, using a deep learning approach (LCF-BERT-CDM) to achieve 82.65% Macro-F1, and finds that positive sentiment increases while negative sentiment decreases with more review rounds.

arXiv:2606.24188v1 Announce Type: new Abstract: Mining sentiment information from the textual content of peer review comments offers valuable insights into the scientific evaluation process. However, previous studies are often constrained by coarse-grained analysis and the lack of differentiation across review rounds. Notably, the dynamic shifts in reviewers' focus and sentiment tendencies throughout multiple review stages remain underexplored. To address this gap, the present study investigates the distribution and evolution of aspect-level sentiments and examines their correlation with the number of review rounds. We begin by segmenting the multi-round review comments of 11,063 accepted papers from Nature Communications and identifying fine-grained review aspect clusters. A manually annotated corpus of approximately 5,000 review sentences is then constructed. Using this dataset, we train a series of deep learning-based aspect sentiment classification models. Among them, the LCF-BERT-CDM model achieves the best performance, with a Macro-F1 score of 82.65%. Subsequent statistical analysis reveals a consistent trend: as the number of review rounds increases, the proportion of positive sentiments rises, while negative sentiments decline. Correlation analysis further indicates that aspect sentiment scores are negatively associated with the total number of review rounds. Key aspects exhibiting stronger correlations include "experiments", "research significance" and "result analysis".
Original Article
View Cached Full Text

Cached at: 06/24/26, 07:45 AM

# Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach
Source: [https://arxiv.org/abs/2606.24188](https://arxiv.org/abs/2606.24188)
[View PDF](https://arxiv.org/pdf/2606.24188)

> Abstract:Mining sentiment information from the textual content of peer review comments offers valuable insights into the scientific evaluation process\. However, previous studies are often constrained by coarse\-grained analysis and the lack of differentiation across review rounds\. Notably, the dynamic shifts in reviewers' focus and sentiment tendencies throughout multiple review stages remain underexplored\. To address this gap, the present study investigates the distribution and evolution of aspect\-level sentiments and examines their correlation with the number of review rounds\. We begin by segmenting the multi\-round review comments of 11,063 accepted papers from Nature Communications and identifying fine\-grained review aspect clusters\. A manually annotated corpus of approximately 5,000 review sentences is then constructed\. Using this dataset, we train a series of deep learning\-based aspect sentiment classification models\. Among them, the LCF\-BERT\-CDM model achieves the best performance, with a Macro\-F1 score of 82\.65%\. Subsequent statistical analysis reveals a consistent trend: as the number of review rounds increases, the proportion of positive sentiments rises, while negative sentiments decline\. Correlation analysis further indicates that aspect sentiment scores are negatively associated with the total number of review rounds\. Key aspects exhibiting stronger correlations include "experiments", "research significance" and "result analysis"\.

## Submission history

From: Chengzhi Zhang \[[view email](https://arxiv.org/show-email/2dec3645/2606.24188)\] **\[v1\]**Tue, 23 Jun 2026 06:14:00 UTC \(40,598 KB\)

Similar Articles

Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews

arXiv cs.CL

Sem-Detect introduces a method to distinguish AI-generated peer reviews from human-written ones by combining textual features with claim-level semantic analysis. It achieves a 25.5% improvement in true positive rate at 0.1% false positive rate over baselines, and shows that LLM-refined human reviews retain distinct semantic signals, with fewer than 3.5% misclassified as AI-generated.

Unsupervised sentiment neuron

OpenAI Blog

OpenAI demonstrates an unsupervised system that learns sentiment representation by training a multiplicative LSTM to predict the next character in Amazon reviews, achieving state-of-the-art sentiment analysis on Stanford Sentiment Treebank (91.8% accuracy) while requiring 30-100x fewer labeled examples than supervised approaches. The model discovers a distinct 'sentiment neuron' that captures sentiment information and can be directly manipulated to control text generation sentiment.

Self-Evolving Deep Research via Joint Generation and Evaluation

arXiv cs.CL

Researchers from HKUST, ByteDance, and UCL propose SCORE, a co-evolutionary training framework that jointly trains an LLM as both a deep research report generator and an evaluator, using a meta-harness to dynamically adjust evaluation difficulty and prevent reward saturation. Experiments show consistent improvement in open-ended research report quality.