cs.LGOct 30, 2026

Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning

Authors: Mahmoud S. Mayaleh, Samer A. Mayaleh

Organizations: National Conservatory of Arts and Crafts (CNAM), Paris, France · An-Najah National University, Nablus, Palestine

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.

Figures & tables

Explore similar work

CardsList
  1. Maximizing Generalization: The Effect of Different Augmentation Techniques on Lightweight Vision Transformer for Bengali Character Classification

    Mar 3, 2026Rafi Hassan Chowdhury, Naimul Haque, Kaniz FatihaData AugmentationOptical Character Recognition

  2. Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement

    Mar 5, 2026Brian Jing Hong Nge, Stefan Su, Thanh Thi Nguyen +3Hate Speech DetectionData Augmentation

  3. Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches

    Oct 11, 2026Tanvi Somani, Aryan Babare, Samyak Bora +2Sentiment AnalysisLow-Resource Language Processing