Improved binary crocodiles hunting strategy optimization for feature selection in sentiment analysis

被引:0
作者
Bekhouche, Maamar [1 ]
Haouassi, Hichem [1 ]
Bakhouche, Abdelaali [1 ]
Rahab, Hichem [1 ]
Mahdaoui, Rafik [1 ]
机构
[1] Abbes Laghrour Univ, Dept Math & Comp Sci, ICOSI Lab, Khenchela, Algeria
关键词
Sentiment analysis; Opinion mining; feature selection; swarm-based intelligence; crocodiles hunting strategy optimization algorithm; Opposition-based learning; CLASSIFICATION;
D O I
10.3233/JIFS-222192
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Feature Selection (FS) for Sentiment Analysis (SA) becomes a complex problem because of the large-sized learning datasets. However, to reduce the data dimensionality, researchers have focused on FS using swarm intelligence approaches that reflect the best classification performance. Crocodiles Hunting Strategy (CHS), a novel swarm-based meta-heuristic that simulates the crocodiles' hunting behaviour, has demonstrated excellent optimization results. Hence, in this work, two FS algorithms, i.e., Binary CHS (BCHS) and Improved BCHS (IBCHS) based on original CHS were applied for FS in the SA field. In IBCHS, the opposition-based learning technique is applied in the initialization and displacement phases to enhance the search space exploration ability of the IBCHS. The two proposed approaches were evaluated using six well-known corpora in the SA area (Semeval-2016, Semeval-2017, Sanders, Stanford, PMD, and MRD). The obtained result showed that IBCHS outperformed BCHS regarding search capability and convergence speed. The comparison results of IBCHS to several recent state-of-the-art approaches show that IBCHS surpassed other approaches in almost all used corpora. The comprehensive results reveal that the use of OBL in BCHS greatly impacts the performance of BCHS by enhancing the diversity of the population and the exploitation ability, which improves the convergence of the IBCHS.
引用
收藏
页码:369 / 389
页数:21
相关论文
共 50 条
[41]   Binary Horse Optimization Algorithm for Feature Selection [J].
Moldovan, Dorin .
ALGORITHMS, 2022, 15 (05)
[42]   Binary feature mask optimization for feature selection [J].
Lorasdagi, Mehmet E. ;
Turali, Mehmet Y. ;
Kozat, Suleyman S. .
Neural Computing and Applications, 2025, 37 (06) :5155-5167
[43]   Efficient Twitter Sentiment Analysis System with Feature Selection and Classifier Ensemble [J].
Fouad, Mohammed M. ;
Gharib, Tarek F. ;
Mashat, Abdulfattah S. .
INTERNATIONAL CONFERENCE ON ADVANCED MACHINE LEARNING TECHNOLOGIES AND APPLICATIONS (AMLTA2018), 2018, 723 :516-527
[44]   Metaheuristic and evolutionary methods for Feature Selection in Sentiment Analysis (a comparative study) [J].
Ighazran, Hasna ;
Alaoui, Larbi ;
Boujiha, Tarik .
2018 INTERNATIONAL SYMPOSIUM ON ADVANCED ELECTRICAL AND COMMUNICATION TECHNOLOGIES (ISAECT), 2018,
[45]   Sentiment Analysis of Movie Reviews: A study on Feature Selection & Classification Algorithms [J].
Sahu, Tirath Prasad ;
Ahuja, Sanjeev .
2016 INTERNATIONAL CONFERENCE ON MICROELECTRONICS, COMPUTING AND COMMUNICATIONS (MICROCOM), 2016,
[46]   Improved Sentiment Analysis for Teaching Evaluation Using Feature Selection and Voting Ensemble Learning Integration [J].
Pong-Inwong, Chakrit ;
Kaewmak, Konpusit .
2016 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2016, :1222-1225
[47]   Swarm Intelligence-Based Feature Selection: An Improved Binary Grey Wolf Optimization Method [J].
Li, Wenqu ;
Kang, Hui ;
Feng, Tie ;
Li, Jiahui ;
Yue, Zhiru ;
Sun, Geng .
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT III, 2021, 12817 :98-110
[48]   Bio-Inspired Feature Selection via an Improved Binary Golden Jackal Optimization Algorithm [J].
Feng, Jinghui ;
Zhang, Xukun ;
Zhang, Lihua .
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT II, KSEM 2024, 2024, 14885 :58-71
[49]   IWD Based Feature Selection Algorithm for Sentiment Analysis [J].
Parlar, Tuba ;
Sarac, Esra .
ELEKTRONIKA IR ELEKTROTECHNIKA, 2019, 25 (01) :54-58
[50]   Feature selection through binary brain storm optimization [J].
Papa, Joao P. ;
Rosa, Gustavo H. ;
de Souza, Andre N. ;
Afonso, Luis C. S. .
COMPUTERS & ELECTRICAL ENGINEERING, 2018, 72 :468-481