Improved whale optimization algorithm for feature selection in Arabic sentiment analysis
To help individuals or companies make a systematic and more accurate decisions, sentiment analysis (SA) is used to evaluate the polarity of reviews. In SA, feature selection phase is an important phase for machine learning classifiers specifically when the datasets used in training is huge. Whale Op...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Springer
2019
|
| Subjects: |
| _version_ | 1796961781373992960 |
|---|---|
| author | Tubishat, Mohammad Abushariah, Mohammad A.M. Idris, Norisma Aljarah, Ibrahim |
| author_facet | Tubishat, Mohammad Abushariah, Mohammad A.M. Idris, Norisma Aljarah, Ibrahim |
| author_sort | Tubishat, Mohammad |
| collection | UM |
| description | To help individuals or companies make a systematic and more accurate decisions, sentiment analysis (SA) is used to evaluate the polarity of reviews. In SA, feature selection phase is an important phase for machine learning classifiers specifically when the datasets used in training is huge. Whale Optimization Algorithm (WOA) is one of the recent metaheuristic optimization algorithm that mimics the whale hunting mechanism. However, WOA suffers from the same problem faced by many other optimization algorithms and tend to fall in local optima. To overcome these problems, two improvements for WOA algorithm are proposed in this paper. The first improvement includes using Elite Opposition-Based Learning (EOBL) at initialization phase of WOA. The second improvement involves the incorporation of evolutionary operators from Differential Evolution algorithm at the end of each WOA iteration including mutation, crossover, and selection operators. In addition, we also used Information Gain (IG) as a filter features selection technique with WOA using Support Vector Machine (SVM) classifier to reduce the search space explored by WOA. To verify our proposed approach, four Arabic benchmark datasets for sentiment analysis are used since there are only a few studies in sentiment analysis conducted for Arabic language as compared to English. The proposed algorithm is compared with six well-known optimization algorithms and two deep learning algorithms. The comprehensive experiments results show that the proposed algorithm outperforms all other algorithms in terms of sentiment analysis classification accuracy through finding the best solutions, while its also minimizes the number of selected features. © 2018, Springer Science+Business Media, LLC, part of Springer Nature. |
| first_indexed | 2024-03-06T05:59:16Z |
| format | Article |
| id | um.eprints-23225 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:59:16Z |
| publishDate | 2019 |
| publisher | Springer |
| record_format | dspace |
| spelling | um.eprints-232252019-12-16T04:03:59Z http://eprints.um.edu.my/23225/ Improved whale optimization algorithm for feature selection in Arabic sentiment analysis Tubishat, Mohammad Abushariah, Mohammad A.M. Idris, Norisma Aljarah, Ibrahim QA75 Electronic computers. Computer science To help individuals or companies make a systematic and more accurate decisions, sentiment analysis (SA) is used to evaluate the polarity of reviews. In SA, feature selection phase is an important phase for machine learning classifiers specifically when the datasets used in training is huge. Whale Optimization Algorithm (WOA) is one of the recent metaheuristic optimization algorithm that mimics the whale hunting mechanism. However, WOA suffers from the same problem faced by many other optimization algorithms and tend to fall in local optima. To overcome these problems, two improvements for WOA algorithm are proposed in this paper. The first improvement includes using Elite Opposition-Based Learning (EOBL) at initialization phase of WOA. The second improvement involves the incorporation of evolutionary operators from Differential Evolution algorithm at the end of each WOA iteration including mutation, crossover, and selection operators. In addition, we also used Information Gain (IG) as a filter features selection technique with WOA using Support Vector Machine (SVM) classifier to reduce the search space explored by WOA. To verify our proposed approach, four Arabic benchmark datasets for sentiment analysis are used since there are only a few studies in sentiment analysis conducted for Arabic language as compared to English. The proposed algorithm is compared with six well-known optimization algorithms and two deep learning algorithms. The comprehensive experiments results show that the proposed algorithm outperforms all other algorithms in terms of sentiment analysis classification accuracy through finding the best solutions, while its also minimizes the number of selected features. © 2018, Springer Science+Business Media, LLC, part of Springer Nature. Springer 2019 Article PeerReviewed Tubishat, Mohammad and Abushariah, Mohammad A.M. and Idris, Norisma and Aljarah, Ibrahim (2019) Improved whale optimization algorithm for feature selection in Arabic sentiment analysis. Applied Intelligence, 49 (5). pp. 1688-1707. ISSN 0924-669X, DOI https://doi.org/10.1007/s10489-018-1334-8 <https://doi.org/10.1007/s10489-018-1334-8>. https://doi.org/10.1007/s10489-018-1334-8 doi:10.1007/s10489-018-1334-8 |
| spellingShingle | QA75 Electronic computers. Computer science Tubishat, Mohammad Abushariah, Mohammad A.M. Idris, Norisma Aljarah, Ibrahim Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title | Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title_full | Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title_fullStr | Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title_full_unstemmed | Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title_short | Improved whale optimization algorithm for feature selection in Arabic sentiment analysis |
| title_sort | improved whale optimization algorithm for feature selection in arabic sentiment analysis |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT tubishatmohammad improvedwhaleoptimizationalgorithmforfeatureselectioninarabicsentimentanalysis AT abushariahmohammadam improvedwhaleoptimizationalgorithmforfeatureselectioninarabicsentimentanalysis AT idrisnorisma improvedwhaleoptimizationalgorithmforfeatureselectioninarabicsentimentanalysis AT aljarahibrahim improvedwhaleoptimizationalgorithmforfeatureselectioninarabicsentimentanalysis |