arXiv cs.CL· Mahmoud S. Mayaleh, Samer A. Mayaleh·· 11 小时前AI 评分20
通过数据增强与迁移学习提升小数据集情感分类性能
Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning
AI 导读
研究对比了 EDA、回译和上下文 token 替换三种数据增强策略在传统机器学习分类器（Logistic Regression、Random Forest）与 BERT 上的效果，所有方法均带来性能提升。上下文增强对 BERT 提升最稳定，EDA 和回译对传统分类器收益更大，为按模型类型和小数据集规模选择增强方法提供了实证依据。
正文 · 原文
Abstract:Small-scale sentiment classification often suffers from data scarcity, which limits the generalization ability of the models. This study evaluates and compares the effectiveness of three data augmentation strategies: Easy Data Augmentation (EDA), back-translation, and contextual token substitution (nlpaug-style), with both traditional machine learning classifiers (Logistic Regression, Random Forest) and transformer-based models (BERT). We perform a comprehensive empirical comparison with low-resource sentiment datasets by summarizing the results of recent studies and performing targeted head-to-head experiments. Our findings indicate that all augmentation methods improve performance. Contextual augmentation yields the most consistent gains for BERT models, while EDA and back-translation provide greater benefits for traditional classifiers. These insights help guide the selection of data augmentation techniques tailored to model type and dataset size, filling a critical gap in research on data augmentation for sentiment classification on small datasets.
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.41518 [cs.LG] |
| (or arXiv:2610.41518v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41518 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Discover Artificial Intelligence 6 (2026) 127 |
| Related DOI: | https://doi.org/10.1007/s44163-025-00813-9
DOI(s) linking to related resources |
Submission history
From: Mahmoud S. Mayaleh [view email]
[v1]
Fri, 30 Oct 2026 10:08:46 UTC (551 KB)
来源：arXiv cs.CL · arxiv.org