Learning an Efficient Text Augmentation Strategy: A Case Study in Sentiment Analysis

Contemporary machine learning models, like deep neural networks, require substantial labeled datasets for proper training. However, in areas such as natural language processing, a shortage of labeled data can lead to overfitting. To address this challenge, data augmentation, which involves transforming data points to maintain class labels and provide additional valuable information, has become an effective strategy. In this paper, a deep reinforcement learning-based text augmentation method for sentiment analysis was introduced, combining reinforcement learning with deep learning. The technique uses Deep Q-Network (DQN) as the reinforcement learning method to search for an efficient augmentation strategy, employing four text augmentation transformations: random deletion, synonym replacement, random swapping, and random insertion. Additionally, various deep learning networks, including CNN, Bi-LSTM, Transformer, BERT, and XLNet, were evaluated for the training phase. Experimental findings show that the proposed technique can achieve an accuracy of ۶۵.۱% with only ۲۰% of the dataset and ۶۹.۳% with ۴۰% of the dataset. Furthermore, with just ۱۰% of the dataset, the method yields an F۱-score of ۶۲.۱%, rising to ۶۹.۱% with ۴۰% of the dataset, outperforming previous approaches. Evaluation on the SemEval dataset demonstrates that reinforcement learning can efficiently augment text datasets for improved sentiment analysis results.

Keywords:

Data Augmentation , Sentiment analysis , Deep reinforcement learning , Neural Network , DQN Algorithm