Exploiting Stacked Autoencoders for Improved Sentiment Analysis
Sentiment analysis is an ongoing research field within the discipline of data mining. The majority of academics employ deep learning models for sentiment analysis due to their ability to self-learn and process vast amounts of data. However, the performance of deep learning models depends on the valu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/23/12380 |
| _version_ | 1827643381839298560 |
|---|---|
| author | Kanwal Ahmed Muhammad Imran Nadeem Dun Li Zhiyun Zheng Yazeed Yasin Ghadi Muhammad Assam Heba G. Mohamed |
| author_facet | Kanwal Ahmed Muhammad Imran Nadeem Dun Li Zhiyun Zheng Yazeed Yasin Ghadi Muhammad Assam Heba G. Mohamed |
| author_sort | Kanwal Ahmed |
| collection | DOAJ |
| description | Sentiment analysis is an ongoing research field within the discipline of data mining. The majority of academics employ deep learning models for sentiment analysis due to their ability to self-learn and process vast amounts of data. However, the performance of deep learning models depends on the values of the hyperparameters. Determining suitable values for hyperparameters is a cumbersome task. The goal of this study is to increase the accuracy of stacked autoencoders for sentiment analysis using a heuristic optimization approach. In this study, we propose a hybrid model GA(SAE)-SVM using a genetic algorithm (GA), stacked autoencoder (SAE), and support vector machine (SVM) for fine-grained sentiment analysis. Features are extracted using continuous bag-of-words (CBOW), and then input into the SAE. In the proposed GA(SAE)-SVM, the hyperparameters of the SAE algorithm are optimized using GA. The features extracted by SAE are input into the SVM for final classification. A comparison is performed with a random search and grid search for parameter optimization. GA optimization is faster than grid search, and selects more optimal values than random search, resulting in improved accuracy. We evaluate the performance of the proposed model on eight benchmark datasets. The proposed model outperformed when compared to the baseline and state-of-the-art techniques. |
| first_indexed | 2024-03-09T17:52:37Z |
| format | Article |
| id | doaj.art-b55a5a9e496942adb8e74ba3d75079e8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:52:37Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b55a5a9e496942adb8e74ba3d75079e82023-11-24T10:35:32ZengMDPI AGApplied Sciences2076-34172022-12-0112231238010.3390/app122312380Exploiting Stacked Autoencoders for Improved Sentiment AnalysisKanwal Ahmed0Muhammad Imran Nadeem1Dun Li2Zhiyun Zheng3Yazeed Yasin Ghadi4Muhammad Assam5Heba G. Mohamed6School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaDepartment of Computer Science and Software Engineering, Al Ain University, Al Ain 15551, United Arab EmiratesDepartment of Software Engineering, University of Science and Technology Bannu, Bannu 28100, PakistanDepartment of Electrical Engineering, College of Engineering, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaSentiment analysis is an ongoing research field within the discipline of data mining. The majority of academics employ deep learning models for sentiment analysis due to their ability to self-learn and process vast amounts of data. However, the performance of deep learning models depends on the values of the hyperparameters. Determining suitable values for hyperparameters is a cumbersome task. The goal of this study is to increase the accuracy of stacked autoencoders for sentiment analysis using a heuristic optimization approach. In this study, we propose a hybrid model GA(SAE)-SVM using a genetic algorithm (GA), stacked autoencoder (SAE), and support vector machine (SVM) for fine-grained sentiment analysis. Features are extracted using continuous bag-of-words (CBOW), and then input into the SAE. In the proposed GA(SAE)-SVM, the hyperparameters of the SAE algorithm are optimized using GA. The features extracted by SAE are input into the SVM for final classification. A comparison is performed with a random search and grid search for parameter optimization. GA optimization is faster than grid search, and selects more optimal values than random search, resulting in improved accuracy. We evaluate the performance of the proposed model on eight benchmark datasets. The proposed model outperformed when compared to the baseline and state-of-the-art techniques.https://www.mdpi.com/2076-3417/12/23/12380data miningnatural language processingtext miningtext analysisweb mining |
| spellingShingle | Kanwal Ahmed Muhammad Imran Nadeem Dun Li Zhiyun Zheng Yazeed Yasin Ghadi Muhammad Assam Heba G. Mohamed Exploiting Stacked Autoencoders for Improved Sentiment Analysis Applied Sciences data mining natural language processing text mining text analysis web mining |
| title | Exploiting Stacked Autoencoders for Improved Sentiment Analysis |
| title_full | Exploiting Stacked Autoencoders for Improved Sentiment Analysis |
| title_fullStr | Exploiting Stacked Autoencoders for Improved Sentiment Analysis |
| title_full_unstemmed | Exploiting Stacked Autoencoders for Improved Sentiment Analysis |
| title_short | Exploiting Stacked Autoencoders for Improved Sentiment Analysis |
| title_sort | exploiting stacked autoencoders for improved sentiment analysis |
| topic | data mining natural language processing text mining text analysis web mining |
| url | https://www.mdpi.com/2076-3417/12/23/12380 |
| work_keys_str_mv | AT kanwalahmed exploitingstackedautoencodersforimprovedsentimentanalysis AT muhammadimrannadeem exploitingstackedautoencodersforimprovedsentimentanalysis AT dunli exploitingstackedautoencodersforimprovedsentimentanalysis AT zhiyunzheng exploitingstackedautoencodersforimprovedsentimentanalysis AT yazeedyasinghadi exploitingstackedautoencodersforimprovedsentimentanalysis AT muhammadassam exploitingstackedautoencodersforimprovedsentimentanalysis AT hebagmohamed exploitingstackedautoencodersforimprovedsentimentanalysis |