Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application
(1) Background: sentiment analysis is a computational technique employed to discern individuals opinions, attitudes, emotions, and intentions concerning a subject by analyzing reviews. Machine learning-based sentiment analysis methods, such as Support Vector Machine (SVM) classification, have proven...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/17/3765 |
| _version_ | 1827728062426382336 |
|---|---|
| author | Ewen Hokijuliandy Herlina Napitupulu Firdaniza |
| author_facet | Ewen Hokijuliandy Herlina Napitupulu Firdaniza |
| author_sort | Ewen Hokijuliandy |
| collection | DOAJ |
| description | (1) Background: sentiment analysis is a computational technique employed to discern individuals opinions, attitudes, emotions, and intentions concerning a subject by analyzing reviews. Machine learning-based sentiment analysis methods, such as Support Vector Machine (SVM) classification, have proven effective in opinion classification. Feature selection methods have been employed to enhance model performance and efficiency, with the Chi-Square method being a commonly used technique; (2) Methods: this study analyzes user reviews of Indonesia’s National Health Insurance (Mobile JKN) application, evaluating model performance and identifying optimal hyperparameters using the F1-Score metric. Sentiment analysis is conducted using a combined approach of SVM classification and Chi-Square feature selection; (3) Results: the sentiment analysis of user reviews for the Mobile JKN application reveals a predominant tendency towards positive reviews. The best model performance is achieved with an F1-Score of 96.82%, employing hyperparameters where <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>C</mi></semantics></math></inline-formula> is set to 10 and a “linear” kernel; (4) Conclusions: this study highlights the effectiveness of SVM classification and the significance of Chi-Square feature selection in sentiment analysis. The findings offer valuable insights into users’ sentiments regarding the Mobile JKN application, contributing to the improvement of user experience and advancing the field of sentiment analysis. |
| first_indexed | 2024-03-10T23:17:43Z |
| format | Article |
| id | doaj.art-c7100903b3fd4371b0ef51059d9b7966 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T23:17:43Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-c7100903b3fd4371b0ef51059d9b79662023-11-19T08:31:51ZengMDPI AGMathematics2227-73902023-09-011117376510.3390/math11173765Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile ApplicationEwen Hokijuliandy0Herlina Napitupulu1Firdaniza2Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Bandung 45363, IndonesiaDepartment of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Bandung 45363, IndonesiaDepartment of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Bandung 45363, Indonesia(1) Background: sentiment analysis is a computational technique employed to discern individuals opinions, attitudes, emotions, and intentions concerning a subject by analyzing reviews. Machine learning-based sentiment analysis methods, such as Support Vector Machine (SVM) classification, have proven effective in opinion classification. Feature selection methods have been employed to enhance model performance and efficiency, with the Chi-Square method being a commonly used technique; (2) Methods: this study analyzes user reviews of Indonesia’s National Health Insurance (Mobile JKN) application, evaluating model performance and identifying optimal hyperparameters using the F1-Score metric. Sentiment analysis is conducted using a combined approach of SVM classification and Chi-Square feature selection; (3) Results: the sentiment analysis of user reviews for the Mobile JKN application reveals a predominant tendency towards positive reviews. The best model performance is achieved with an F1-Score of 96.82%, employing hyperparameters where <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>C</mi></semantics></math></inline-formula> is set to 10 and a “linear” kernel; (4) Conclusions: this study highlights the effectiveness of SVM classification and the significance of Chi-Square feature selection in sentiment analysis. The findings offer valuable insights into users’ sentiments regarding the Mobile JKN application, contributing to the improvement of user experience and advancing the field of sentiment analysis.https://www.mdpi.com/2227-7390/11/17/3765sentiment analysismachine learningSVMChi-SquarehyperparameterMobile JKN application |
| spellingShingle | Ewen Hokijuliandy Herlina Napitupulu Firdaniza Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application Mathematics sentiment analysis machine learning SVM Chi-Square hyperparameter Mobile JKN application |
| title | Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application |
| title_full | Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application |
| title_fullStr | Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application |
| title_full_unstemmed | Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application |
| title_short | Application of SVM and Chi-Square Feature Selection for Sentiment Analysis of Indonesia’s National Health Insurance Mobile Application |
| title_sort | application of svm and chi square feature selection for sentiment analysis of indonesia s national health insurance mobile application |
| topic | sentiment analysis machine learning SVM Chi-Square hyperparameter Mobile JKN application |
| url | https://www.mdpi.com/2227-7390/11/17/3765 |
| work_keys_str_mv | AT ewenhokijuliandy applicationofsvmandchisquarefeatureselectionforsentimentanalysisofindonesiasnationalhealthinsurancemobileapplication AT herlinanapitupulu applicationofsvmandchisquarefeatureselectionforsentimentanalysisofindonesiasnationalhealthinsurancemobileapplication AT firdaniza applicationofsvmandchisquarefeatureselectionforsentimentanalysisofindonesiasnationalhealthinsurancemobileapplication |