@inproceedings { , title = {Class-decomposition and augmentation for imbalanced data sentiment analysis.}, abstract = {Significant progress has been made in the area of text classification and natural language processing. However, like many other datasets from across different domains, text-based datasets may suffer from class-imbalance. This problem leads to model's bias toward the majority class instances. In this paper, we present a new approach to handle class-imbalance in text data by means of unsupervised learning algorithms. We present class-decomposition using two different unsupervised methods, namely k-means and Density-Based Spatial Clustering of Applications with Noise, applied to two different sentiment analysis data sets. The experimental results show that utilizing clustering to find within-class similarities can lead to significant improvement in learning algorithm's performances as well as reducing the dominance of the majority class instances without causing information loss.}, conference = {2021 International joint conference on neural networks (IJCNN 2021)}, doi = {10.1109/ijcnn52387.2021.9533603}, isbn = {9780738133669}, note = {INFO COMPLETE (Info via IEEExplore alert 23/9/2021 LM) PERMISSION GRANTED (version = AAM; embargo = none; licence = Pub's own: POLICY = https://conferences.ieeeauthorcenter.ieee.org/get-published/post-your-paper/ ) DOCUMENT READY (AAM rec'd from contact 24/9/2021 LM) ADDITIONAL INFO - Contact: Carlos Moreno-Garcia; Eyad Elyan Set Statement (© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.)}, publicationstatus = {Published}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://rgu-repository.worktribe.com/output/1465455}, keyword = {Interactive Machine Vision, Living in a Digital World, Sentiment analysis, Text imbalanced datasets, Class decomposition}, year = {2021}, author = {Moreno-Garcia, Carlos Francisco and Jayne, Chrisina and Elyan, Eyad} }