Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language
This study explores the enhancement of accuracy in Indonesian sentiment analysis by incorporating text segmentation features during the pre-processing phase. One of the most important steps in creating a highquality Bag of Words is to separate Indonesian sentences with no spacing, which is made pos...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
ASPG
2024
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/12117/1/J17676_7aa8913f69426b15d1c915a823c6ac83.pdf |
| _version_ | 1817857257523642368 |
|---|---|
| author | Siti Mujilahwati, Siti Mujilahwati M. Safar, Noor Zuraidin Supriyanto, Catur |
| author_facet | Siti Mujilahwati, Siti Mujilahwati M. Safar, Noor Zuraidin Supriyanto, Catur |
| author_sort | Siti Mujilahwati, Siti Mujilahwati |
| collection | UTHM |
| description | This study explores the enhancement of accuracy in Indonesian sentiment analysis by incorporating text
segmentation features during the pre-processing phase. One of the most important steps in creating a highquality Bag of Words is to separate Indonesian sentences with no spacing, which is made possible by the created text segmentation algorithm. Through the conducted observations and analyses, it was observed that text comments from social media frequently exhibit connected sentences without spacing. The
segmentation process was developed through a matching model utilizing a standard Indonesian word dictionary. Implementation involved testing Indonesian text data related to COVID-19 management, resulting in a substantial increase of 3,036 features. The Bag of Words was then constructed using the Term Frequency-Inverse Document Frequency method. Subsequently, sentiment analysis classification testing was conducted using both deep learning and machine learning models to assess data quality and accuracy. The sentiment analysis accuracy for applying Deep Learning, Support Vector Machine and Naive Bayes is 86.46%, 88.02% and 86.19% respectively. |
| first_indexed | 2024-12-08T07:42:57Z |
| format | Article |
| id | uthm.eprints-12117 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-12-08T07:42:57Z |
| publishDate | 2024 |
| publisher | ASPG |
| record_format | dspace |
| spelling | uthm.eprints-121172024-12-01T03:03:21Z http://eprints.uthm.edu.my/12117/ Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language Siti Mujilahwati, Siti Mujilahwati M. Safar, Noor Zuraidin Supriyanto, Catur P302 - 302.87 Discourse analysis This study explores the enhancement of accuracy in Indonesian sentiment analysis by incorporating text segmentation features during the pre-processing phase. One of the most important steps in creating a highquality Bag of Words is to separate Indonesian sentences with no spacing, which is made possible by the created text segmentation algorithm. Through the conducted observations and analyses, it was observed that text comments from social media frequently exhibit connected sentences without spacing. The segmentation process was developed through a matching model utilizing a standard Indonesian word dictionary. Implementation involved testing Indonesian text data related to COVID-19 management, resulting in a substantial increase of 3,036 features. The Bag of Words was then constructed using the Term Frequency-Inverse Document Frequency method. Subsequently, sentiment analysis classification testing was conducted using both deep learning and machine learning models to assess data quality and accuracy. The sentiment analysis accuracy for applying Deep Learning, Support Vector Machine and Naive Bayes is 86.46%, 88.02% and 86.19% respectively. ASPG 2024 Article PeerReviewed text en http://eprints.uthm.edu.my/12117/1/J17676_7aa8913f69426b15d1c915a823c6ac83.pdf Siti Mujilahwati, Siti Mujilahwati and M. Safar, Noor Zuraidin and Supriyanto, Catur (2024) Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language. Fusion: Practice and Applications (FPA), 15 (2). pp. 145-154. https://doi.org/10.54216/FPA.150213 |
| spellingShingle | P302 - 302.87 Discourse analysis Siti Mujilahwati, Siti Mujilahwati M. Safar, Noor Zuraidin Supriyanto, Catur Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title | Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title_full | Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title_fullStr | Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title_full_unstemmed | Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title_short | Segmentation Word to Improve Performance Sentiment Analysis for Indonesian Language |
| title_sort | segmentation word to improve performance sentiment analysis for indonesian language |
| topic | P302 - 302.87 Discourse analysis |
| url | http://eprints.uthm.edu.my/12117/1/J17676_7aa8913f69426b15d1c915a823c6ac83.pdf |
| work_keys_str_mv | AT sitimujilahwatisitimujilahwati segmentationwordtoimproveperformancesentimentanalysisforindonesianlanguage AT msafarnoorzuraidin segmentationwordtoimproveperformancesentimentanalysisforindonesianlanguage AT supriyantocatur segmentationwordtoimproveperformancesentimentanalysisforindonesianlanguage |