A review: preprocessing techniques and data augmentation for sentiment analysis

Abstract In literature, the machine learning-based studies of sentiment analysis are usually supervised learning which must have pre-labeled datasets to be large enough in certain domains. Obviously, this task is tedious, expensive and time-consuming build, hard handle unseen data. This paper has approached semi-supervised for Vietnamese limited datasets. We summarized many preprocessing techniques were performed clean normalize data, negation handling, intensification handling improve performances. Moreover, data augmentation techniques, generate new from original enrich training without user intervention, also been presented. experiments, we various aspects obtained competitive results may motivate next propositions.