Sentiment Analysis Using Self-Adaptive Stacking Ensemble Method for Classification

International Journal of Electronics and Communication Engineering

© 2024 by SSRG - IJECE Journal

Volume 11 Issue 1

Year of Publication : 2024

Authors : K.R. Srinath, B. Indira

10.14445/23488549/IJECE-V11I1P106

How to Cite?

K.R. Srinath, B. Indira, "Sentiment Analysis Using Self-Adaptive Stacking Ensemble Method for Classification," SSRG International Journal of Electronics and Communication Engineering, vol. 11,  no. 1, pp. 67-85, 2024. Crossref, https://doi.org/10.14445/23488549/IJECE-V11I1P106

Abstract:

The primary purpose of sentiment analysis is to classify the polarity of the data, such as whether the data should be positive, negative, or neutral. Most sentiment analyses used single classifiers, but they do not provide an accurate polarity. There should also be drawbacks, like a lack of keywords, high dimensional space, etc. This paper used the polarized word embedding technique and Remora Optimization algorithm for distance ranking; then, the classification is done by both machine learning and deep learning classifiers that are integrated using the self-adaptive stacking ensemble method to select the finest base classifier and hyper-parameters of base classifiers with the use of the genetic algorithm. Then, the model is trained and tested employing four datasets utilizing cross-validation, and the performance is calculated using recall, accuracy, precision, F1 score, and AUC that is compared using four state-of-the-art models. The comparison shows that the proposed method provides the most accurate predicted value with the highest accuracy of 99.3%.

Keywords:

Sentiment analysis, Word embedding, Attention CNN, Bi-GRU, HSVM, Bayesian network.

References:

[1] Seng Zian, Sameem Abdul Kareem, and Kasturi Dewi Varathan, “An Empirical Evaluation of Stacked Ensembles with Different Meta-Learners in Imbalanced Classification,” IEEE Access, vol. 9, pp. 87434-87452, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Aytuğ Onan, “Sentiment Analysis on Product Reviews Based on Weighted Word Embeddings and Deep Neural Networks,” Concurrency and Computation: Practice and Experience, vol. 33, no. 23, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Duyu Tang, and Meishan Zhang, “Deep Learning in Sentiment Analysis,” Deep Learning in Natural Language Processing, pp. 219- 253, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mohammad Ehsan Basiri et al., “A Novel Fusion-Based Deep Learning Model for Sentiment Analysis of COVID-19 Tweets,” Knowledge-Based Systems, vol. 228, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Weili Jiang et al., “SSEM: A Novel Self-Adaptive Stacking Ensemble Model for Classification,” IEEE Access, vol. 7, pp. 120337- 120349, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] B. Oscar Deho et al., “Sentiment Analysis with Word Embedding,” 2018 IEEE 7^th International Conference on Adaptive Science & Technology (ICAST), Accra, Ghana, pp. 1-4, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Seyed Mahdi Rezaeinia et al., “Sentiment Analysis Based on Improved Pre-Trained Word Embeddings,” Expert Systems with Applications, vol. 117, pp. 139-147, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zufan Zhang, Yang Zou, and Chenquan Gan, “Textual Sentiment Analysis via Three Different Attention Convolutional Neural Networks and Cross-Modality Consistent Regression,” Neurocomputing, vol. 275, pp. 1407-1415, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Mohd Usama et al., “Attention-Based Sentiment Analysis Using Convolutional and Recurrent Neural Network,” Future Generation Computer Systems, vol. 113, pp. 571-578, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yaxing Pan, and Mingfeng Liang, “Chinese Text Sentiment Analysis Based on BI-GRU and Self-Attention,” 2020 IEEE 4^th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chongqing, China, pp. 1983-1988, 2020.
[CrossRef] [Google Scholar] [Publisher Link] 
[11] Huawen Liu et al., “Feature Selection with Dynamic Mutual Information,” Pattern Recognition, vol. 42, no. 7, pp. 1330-1339, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Mohammad Ehsan Basiri et al., “A Novel Method for Sentiment Classification of Drug Reviews Using Fusion of Deep and Machine Learning Techniques,” Knowledge-Based Systems, vol. 198, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Oscar Araque et al., “Enhancing Deep Learning Sentiment Analysis with Ensemble Techniques in Social Applications,” Expert Systems with Applications, vol. 77, pp. 236-246, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Babacar Gaye, Dezheng Zhang, and Aziguli Wulamu, “A Tweet Sentiment Classification Approach Using a Hybrid Stacked Ensemble Technique,” Information, vol. 12, no. 9, pp. 1-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Yasin Gormez et al., “FBSEM: A Novel Feature-Based Stacked Ensemble Method for Sentiment Analysis,” International Journal of Information Technology and Computer Science, vol. 12, no. 6, pp. 11-22, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Basant Subba, and Simpy Kumari, “A Heterogeneous Stacking Ensemble Based Sentiment Analysis Framework Using Multiple Word Embeddings,” Computational Intelligence, vol. 38, no. 2, pp. 530-559, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Azadeh Mohammadi, and Anis Shaverizade, “Ensemble Deep Learning for Aspect-Based Sentiment Analysis,” International Journal of Nonlinear Analysis and Applications, vol. 12, pp. 29-38, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Yanling Zhou et al., “Deep Learning Based Fusion Approach for Hate Speech Detection,” IEEE Access, vol. 8, pp. 128923-128929, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Teragawa Shoryu, Lei Wang, and Ruixin Ma, “A Deep Neural Network Approach using Convolutional Network and Long Short Term Memory for Text Sentiment Classification,” 2021 IEEE 24^th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Dalian, China, pp. 763-768, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Hai Ha Do et al., “Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review,” Expert Systems with Applications, vol. 118, pp. 272-299, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Dejun Zhang et al., “Combining Convolution Neural Network and Bidirectional Gated Recurrent Unit for Sentence Semantic Classification,” IEEE Access, vol. 6, pp. 73750-73759, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Harleen Kaur et al., “A Proposed Sentiment Analysis Deep Learning Algorithm for Analyzing COVID-19 Tweets,” Information Systems Frontiers, vol. 23, pp. 1417-1429, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Mattia Atzeni, and Diego Reforgiato Recupero, “Multi-Domain Sentiment Analysis with Mimicked and Polarized Word Embeddings for Human-Robot Interaction,” Future Generation Computer Systems, vol. 110, pp. 984-999, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Shibaprasad Sen et al., “A Bi-Stage Feature Selection Approach for COVID-19 Prediction Using Chest CT Images,” Applied Intelligence, vol. 51, pp. 8985-9000, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Hastari Utama, “Sentiment Analysis in Airline Tweets Using Mutual Information for Feature Selection,” 2019 4^th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Yogyakarta, Indonesia, pp. 295- 300, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Jorge R. Vergara, and Pablo A. Estévez, “A Review of Feature Selection Methods Based on Mutual Information,” Neural Computing and Applications, vol. 24, pp. 175-186. 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Heming Jia, Xiaoxu Peng, and Chunbo Lang, “Remora Optimization Algorithm,” Expert Systems with Applications, vol. 185, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Gonzalo A. Ruz, Pablo A. Henríquez, and Aldo Mascareño, “Sentiment Analysis of Twitter Data during Critical Events through Bayesian Networks Classifiers,” Future Generation Computer Systems, vol. 106, pp. 92-104, 2020.
[CrossRef] [Google Scholar] [Publisher Link]