Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/91412
PIRA download icon_1.1View/Download Full Text
Title: Lexical data augmentation for sentiment analysis
Authors: Xiang, R 
Chersoni, E 
Lu, Q 
Huang, CR 
Li, W 
Long, Y
Issue Date: 2021
Source: Journal of the Association for Information Science and Technology, 2021, Early View, https://doi.org/10.1002/asi.24493
Abstract: Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part-of-speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic-based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution-based data augmentation methods, one of which is thesaurus-based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST-2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM-AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well-designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms.
Publisher: John Wiley & Sons
Journal: Journal of the Association for Information Science and Technology 
ISSN: 2330-1635
EISSN: 2330-1643
DOI: 10.1002/asi.24493
Rights: © 2021 The Authors. Journal of the Association for Information Science and Technology published by Wiley Periodicals LLC on behalf of Association for Information Science and Technology. This is an open access article under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
The following publication Xiang, R., Chersoni, E.,Lu, Q., Huang, C.-R., Li, W., & Long, Y. (2021).Lexical data augmentation for sentiment analysis.Journal of the Association for Information Scienceand Technology, 1–16 is available at https://doi.org/10.1002/asi.24493
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
asi.24493.pdf2.47 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

15
Citations as of May 15, 2022

SCOPUSTM   
Citations

2
Citations as of May 12, 2022

WEB OF SCIENCETM
Citations

2
Citations as of May 12, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.