Tailored text augmentation for sentiment analysis

• Main Authors: Feng, Zijian, Zhou, Hanzhang, Zhu, Zixiao, Mao, Kezhi
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Sentiment Analysis; Text Augmentation
• Online Access: https://hdl.handle.net/10356/162087
• Institution: Nanyang Technological University

In synonym replacement-based data augmentation techniques for natural language processing tasks, words in a sentence are often sampled randomly with equal probability. In this paper, we propose a novel data augmentation technique named Tailored Text Argumentation (TTA) for sentiment analysis. It has...