A review: preprocessing techniques and data augmentation for sentiment analysis
Authors:
Open Access
- 6 January 2021
- journal article
- review article
- Published by Springer Nature in Computational Social Networks
- Vol. 8 (1) , 1-16
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 to build, and hard to handle unseen data. This paper has approached semi-supervised learning for Vietnamese sentiment analysis which has limited datasets. We have summarized many preprocessing techniques which were performed to clean and normalize data, negation handling, intensification handling to improve the performances. Moreover, data augmentation techniques, which generate new data from the original data to enrich training data without user intervention, have also been presented. In experiments, we have performed various aspects and obtained competitive results which may motivate the next propositions.Keywords
This publication has 23 references indexed in Scilit:
- A Comparison of Pre-processing Techniques for Twitter Sentiment Analysis2017
- A survey of multimodal sentiment analysisImage and Vision Computing, 2017
- Comparison Research on Text Pre-processing Methods on Twitter Sentiment AnalysisIEEE Access, 2017
- Data Augmentation for Low-Resource Neural Machine Translation2017
- Role of Text Pre-processing in Twitter Sentiment AnalysisProcedia Computer Science, 2016
- Improving Neural Machine Translation Models with Monolingual Data2016
- Sentiment expression via emoticons on social media2015
- Dual Sentiment Analysis: Considering Two Sides of One ReviewIEEE Transactions on Knowledge and Data Engineering, 2015
- GTI: An Unsupervised Approach for Sentiment Analysis in Twitter2015
- Sentiment analysis algorithms and applications: A surveyAin Shams Engineering Journal, 2014