Evaluating the Effectiveness of Data Augmentation for Emotion Classification in Low-Resource Settings
This work addresses emotion classification for low-resource datasets, but it is incremental as it applies existing augmentation methods to a specific domain.
The study tackled the problem of improving emotion classification in low-resource settings by evaluating data augmentation techniques, finding that Back Translation outperformed autoencoder-based methods and increased performance with multiple examples per instance.
Data augmentation has the potential to improve the performance of machine learning models by increasing the amount of training data available. In this study, we evaluated the effectiveness of different data augmentation techniques for a multi-label emotion classification task using a low-resource dataset. Our results showed that Back Translation outperformed autoencoder-based approaches and that generating multiple examples per training instance led to further performance improvement. In addition, we found that Back Translation generated the most diverse set of unigrams and trigrams. These findings demonstrate the utility of Back Translation in enhancing the performance of emotion classification models in resource-limited situations.