Using back-and-forth translation to create artificial augmented textual data for sentiment analysis models
Thomas A.J. Body, Xiaohui Tao, Yuefeng Li, Lin Li, Ning Zhong · Expert Systems with Applications · 2021
Sentiment analysis classification models trained using neural networks require large amounts of data, but collecting these datasets requires significant time and resources. Although artificial data has been used successfully in computer vision, there are few effective and generalizable methods for creating artificial augmented text data. In this paper, a text based data augmentation method is proposed called back-and-forth translation that can be used to artificially increase the size of any natural language dataset. By creating augmented text data and adding it to the original dataset, it is demonstrated by empirical experiments that back-and-forth translation data augmentation can reduce the error rate in binary sentiment classification models by up to 3.4%. These results are shown to be statistically significant.