Intelligent Hybrid Feature Selection for Textual Sentiment Classification
Sentiment Analysis (SA) aims to extract useful information from online Unstructured User-Generated Contents (UUGC) and classify them into positive and negative classes. State-of-the-art techniques for SA suffer a high dimensional feature space because of noisy and irrelevant features from the UUGC....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9564065/ |
| _version_ | 1819021097328181248 |
|---|---|
| author | Jawad Khan Aftab Alam Youngmoon Lee |
| author_facet | Jawad Khan Aftab Alam Youngmoon Lee |
| author_sort | Jawad Khan |
| collection | DOAJ |
| description | Sentiment Analysis (SA) aims to extract useful information from online Unstructured User-Generated Contents (UUGC) and classify them into positive and negative classes. State-of-the-art techniques for SA suffer a high dimensional feature space because of noisy and irrelevant features from the UUGC. Researchers have also proposed feature extraction and selection techniques to reduce high dimensional feature space, but they fall short in extracting and selecting the most effective sentiment features for sentiment model learning. Effective feature extraction and selection are significant for the SA because they can boost the learning algorithm’s predictive performance while reducing the high-dimensional feature space. To address these concerns, we propose an Intelligent Hybrid Feature Selection for Sentiment Analysis (IHFSSA) based on ensemble learning methods. IHFSSA first identifies sentiment features in the review text utilizing Penn Treebank part-of-speech tagset and integrated Wide Coverage Sentiment Lexicons (WCSL). The sentiment features subset is then selected employing a fast and simple rank-based ensemble of multiple filters feature selection method. The selected sentiment features are further refined by applying a wrapper-based backward feature selection method. Finally, for textual sentiment classification, the well-known classification algorithms Support Vector Machine (SVM), Naive Bayes (NB), Generalized Linear Model (GLM) are trained in the ensemble model on the refined sentiment feature set. The in-depth evaluation using heterogeneous domain benchmark datasets demonstrates that IHFSSA outperforms existing SA techniques. |
| first_indexed | 2024-12-21T04:01:41Z |
| format | Article |
| id | doaj.art-8c4a410a7e6249259717bb169ab46fd7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T04:01:41Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8c4a410a7e6249259717bb169ab46fd72022-12-21T19:16:42ZengIEEEIEEE Access2169-35362021-01-01914059014060810.1109/ACCESS.2021.31189829564065Intelligent Hybrid Feature Selection for Textual Sentiment ClassificationJawad Khan0https://orcid.org/0000-0001-8263-7213Aftab Alam1https://orcid.org/0000-0001-9222-2468Youngmoon Lee2https://orcid.org/0000-0002-6393-2994Department of Robotics, Hanyang University, Ansan-si, South KoreaDivision of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, QatarDepartment of Robotics, Hanyang University, Ansan-si, South KoreaSentiment Analysis (SA) aims to extract useful information from online Unstructured User-Generated Contents (UUGC) and classify them into positive and negative classes. State-of-the-art techniques for SA suffer a high dimensional feature space because of noisy and irrelevant features from the UUGC. Researchers have also proposed feature extraction and selection techniques to reduce high dimensional feature space, but they fall short in extracting and selecting the most effective sentiment features for sentiment model learning. Effective feature extraction and selection are significant for the SA because they can boost the learning algorithm’s predictive performance while reducing the high-dimensional feature space. To address these concerns, we propose an Intelligent Hybrid Feature Selection for Sentiment Analysis (IHFSSA) based on ensemble learning methods. IHFSSA first identifies sentiment features in the review text utilizing Penn Treebank part-of-speech tagset and integrated Wide Coverage Sentiment Lexicons (WCSL). The sentiment features subset is then selected employing a fast and simple rank-based ensemble of multiple filters feature selection method. The selected sentiment features are further refined by applying a wrapper-based backward feature selection method. Finally, for textual sentiment classification, the well-known classification algorithms Support Vector Machine (SVM), Naive Bayes (NB), Generalized Linear Model (GLM) are trained in the ensemble model on the refined sentiment feature set. The in-depth evaluation using heterogeneous domain benchmark datasets demonstrates that IHFSSA outperforms existing SA techniques.https://ieeexplore.ieee.org/document/9564065/Sentiment classificationhybrid feature selectionensemble learninglinguistic semantic ruleswide coverage sentiment lexiconsnatural language processing |
| spellingShingle | Jawad Khan Aftab Alam Youngmoon Lee Intelligent Hybrid Feature Selection for Textual Sentiment Classification IEEE Access Sentiment classification hybrid feature selection ensemble learning linguistic semantic rules wide coverage sentiment lexicons natural language processing |
| title | Intelligent Hybrid Feature Selection for Textual Sentiment Classification |
| title_full | Intelligent Hybrid Feature Selection for Textual Sentiment Classification |
| title_fullStr | Intelligent Hybrid Feature Selection for Textual Sentiment Classification |
| title_full_unstemmed | Intelligent Hybrid Feature Selection for Textual Sentiment Classification |
| title_short | Intelligent Hybrid Feature Selection for Textual Sentiment Classification |
| title_sort | intelligent hybrid feature selection for textual sentiment classification |
| topic | Sentiment classification hybrid feature selection ensemble learning linguistic semantic rules wide coverage sentiment lexicons natural language processing |
| url | https://ieeexplore.ieee.org/document/9564065/ |
| work_keys_str_mv | AT jawadkhan intelligenthybridfeatureselectionfortextualsentimentclassification AT aftabalam intelligenthybridfeatureselectionfortextualsentimentclassification AT youngmoonlee intelligenthybridfeatureselectionfortextualsentimentclassification |