Machine learning approach to customer sentiment analysis in twitter airline reviews
Customers typically provide both online and physical services they use ratings and reviews. However, the volume of reviews might grow very quickly. The power of machine learning to recognize this kind of data is astounding. Numerous algorithms that could be employed for job of sentiment analysis hav...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2023-01-01
|
| Series: | E3S Web of Conferences |
| Subjects: | |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/85/e3sconf_icenis2023_02044.pdf |
| _version_ | 1797345525719105536 |
|---|---|
| author | Pujo Ariesanto Akhmad Ekka Adi Kusworo Puji Widodo Aris |
| author_facet | Pujo Ariesanto Akhmad Ekka Adi Kusworo Puji Widodo Aris |
| author_sort | Pujo Ariesanto Akhmad Ekka |
| collection | DOAJ |
| description | Customers typically provide both online and physical services they use ratings and reviews. However, the volume of reviews might grow very quickly. The power of machine learning to recognize this kind of data is astounding. Numerous algorithms that could be employed for job of sentiment analysis have been developed to categorize tweets about airline sentiment into positive, neutral, or negative categories, this study compares the effectiveness algorithm for machine learning Naive Bayes (NB), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Adaboost, Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), and Random Forest (RF) dividing the Twitter airline sentiment data into positive, neutral, or negative categories using the TF IDF model. The experiment involved two phases of activity: a classification algorithm utilizing SMOTE and sans SMOTE with Stratified K-Fold CV algorithm. With the RF model, the greatest performance accuracy for SMOTE is 97.56%. Without SMOTE, the RF with a value of 92.21% provides the maximum performance accuracy. The findings demonstrate that SMOTE oversampling can improve sentiment analysis accuracy. |
| first_indexed | 2024-03-08T11:18:55Z |
| format | Article |
| id | doaj.art-ee44bfcdac454827bf292aedd2a7e241 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-03-08T11:18:55Z |
| publishDate | 2023-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-ee44bfcdac454827bf292aedd2a7e2412024-01-26T10:28:00ZengEDP SciencesE3S Web of Conferences2267-12422023-01-014480204410.1051/e3sconf/202344802044e3sconf_icenis2023_02044Machine learning approach to customer sentiment analysis in twitter airline reviewsPujo Ariesanto Akhmad Ekka0Adi Kusworo1Puji Widodo Aris2Doctoral of Information System Department, Diponegoro UniversityPhysics Department, Science and Math Faculty, Diponegoro UniversityInformatics Department, Science and Math Faculty, Diponegoro UniversityCustomers typically provide both online and physical services they use ratings and reviews. However, the volume of reviews might grow very quickly. The power of machine learning to recognize this kind of data is astounding. Numerous algorithms that could be employed for job of sentiment analysis have been developed to categorize tweets about airline sentiment into positive, neutral, or negative categories, this study compares the effectiveness algorithm for machine learning Naive Bayes (NB), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Adaboost, Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), and Random Forest (RF) dividing the Twitter airline sentiment data into positive, neutral, or negative categories using the TF IDF model. The experiment involved two phases of activity: a classification algorithm utilizing SMOTE and sans SMOTE with Stratified K-Fold CV algorithm. With the RF model, the greatest performance accuracy for SMOTE is 97.56%. Without SMOTE, the RF with a value of 92.21% provides the maximum performance accuracy. The findings demonstrate that SMOTE oversampling can improve sentiment analysis accuracy.https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/85/e3sconf_icenis2023_02044.pdfairline reviewssentiment analysismachine learningsmotestratified k-fold cv |
| spellingShingle | Pujo Ariesanto Akhmad Ekka Adi Kusworo Puji Widodo Aris Machine learning approach to customer sentiment analysis in twitter airline reviews E3S Web of Conferences airline reviews sentiment analysis machine learning smote stratified k-fold cv |
| title | Machine learning approach to customer sentiment analysis in twitter airline reviews |
| title_full | Machine learning approach to customer sentiment analysis in twitter airline reviews |
| title_fullStr | Machine learning approach to customer sentiment analysis in twitter airline reviews |
| title_full_unstemmed | Machine learning approach to customer sentiment analysis in twitter airline reviews |
| title_short | Machine learning approach to customer sentiment analysis in twitter airline reviews |
| title_sort | machine learning approach to customer sentiment analysis in twitter airline reviews |
| topic | airline reviews sentiment analysis machine learning smote stratified k-fold cv |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/85/e3sconf_icenis2023_02044.pdf |
| work_keys_str_mv | AT pujoariesantoakhmadekka machinelearningapproachtocustomersentimentanalysisintwitterairlinereviews AT adikusworo machinelearningapproachtocustomersentimentanalysisintwitterairlinereviews AT pujiwidodoaris machinelearningapproachtocustomersentimentanalysisintwitterairlinereviews |