# Data augmentation for low resource sentiment analysis using generative adversarial networks

arXiv: https://arxiv.org/abs/1902.06818 · HTML: https://mlsanity.com/paper/1902.06818/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [Specialized Document Embeddings for Aspect-based Similarity of Research Papers](https://mlsanity.com/paper/2203.14541/) (2022)
- [Transfer Learning for Low-Resource Sentiment Analysis](https://mlsanity.com/paper/2304.04703/) (2023)
- [Will sentiment analysis need subculture? A new data augmentation approach](https://mlsanity.com/paper/2309.00178/) (2023)
- [A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification](https://mlsanity.com/paper/2109.11834/) (2021)
- [Modeling the Graphotactics of Low-Resource Languages Using Sequential GANs](https://mlsanity.com/paper/2210.14409/) (2022)
- [I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection](https://mlsanity.com/paper/2308.04109/) (2023)
- [Evaluation Metrics for Text Data Augmentation in NLP](https://mlsanity.com/paper/2402.06766/) (2024)

## Abstract (arXiv)

Sentiment analysis is a task that may suffer from a lack of data in certain cases, as the datasets are often generated and annotated by humans. In cases where data is inadequate for training discriminative models, generate models may aid training via data augmentation. Generative Adversarial Networks (GANs) are one such model that has advanced the state of the art in several tasks, including as image and text generation. In this paper, I train GAN models on low resource datasets, then use them for the purpose of data augmentation towards improving sentiment classifier generalization. Given the constraints of limited data, I explore various techniques to train the GAN models. I also present an analysis of the quality of generated GAN data as more training data for the GAN is made available. In this analysis, the generated data is evaluated as a test set (against a model trained on real data points) as well as a training set to train classification models. Finally, I also conduct a visual analysis by projecting the generated and the real data into a two-dimensional space using the t-Distributed Stochastic Neighbor Embedding (t-SNE) method.