Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN
Bukalapak is one of the largest marketplaces in Indonesia. Reviews on Bukalapak are only in the form of text, images, videos, and stars without any special filters. Reading and analyzing manually makes it difficult for potential buyers. To help with this, we can extract this review by using aspect-b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2023-06-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | http://jurnal.iaii.or.id/index.php/RESTI/article/view/4751 |
| _version_ | 1827362229628960768 |
|---|---|
| author | Syaiful Imron Esther Irawati Setiawan Joan Santoso Mauridhi Hery Purnomo |
| author_facet | Syaiful Imron Esther Irawati Setiawan Joan Santoso Mauridhi Hery Purnomo |
| author_sort | Syaiful Imron |
| collection | DOAJ |
| description | Bukalapak is one of the largest marketplaces in Indonesia. Reviews on Bukalapak are only in the form of text, images, videos, and stars without any special filters. Reading and analyzing manually makes it difficult for potential buyers. To help with this, we can extract this review by using aspect-based sentiment analysis because an entity cannot be represented by just one sentiment. Several previous research stated that using LSTM-CNN got better results than using LSTM or CNN. In addition, using BERT as word embedding gets better results than using word2vec or glove. For this reason, this study aims to classify aspect-based sentiment analysis from the Bukalapak marketplace with BERT as word embedding and using the LSTM-CNN method, where LSTM is for aspect extraction and CNN for sentiment extraction. Based on testing the LSTM-CNN method, it gets better results than LSTM or CNN. The LSTM-CNN model gets an accuracy of 93.91%. Unbalanced dataset distribution can affect model performance. With the increasing number of datasets used, the accuracy of a model will increase. Classification without using stemming on datasets can increase accuracy by 2.04%. |
| first_indexed | 2024-03-08T07:23:01Z |
| format | Article |
| id | doaj.art-2a3e6582c03d414a8a5f11973ba5a3c0 |
| institution | Directory Open Access Journal |
| issn | 2580-0760 |
| language | English |
| last_indexed | 2024-03-08T07:23:01Z |
| publishDate | 2023-06-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj.art-2a3e6582c03d414a8a5f11973ba5a3c02024-02-02T22:44:02ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602023-06-017358659110.29207/resti.v7i3.47514751Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNNSyaiful Imron0Esther Irawati Setiawan1Joan Santoso2Mauridhi Hery Purnomo3Institut Sains dan Teknologi Terpadu SurabayaInstitut Sains dan Teknologi Terpadu SurabayaInstitut Sains dan Teknologi Terpadu SurabayaInstitut Teknologi Sepuluh NopemberBukalapak is one of the largest marketplaces in Indonesia. Reviews on Bukalapak are only in the form of text, images, videos, and stars without any special filters. Reading and analyzing manually makes it difficult for potential buyers. To help with this, we can extract this review by using aspect-based sentiment analysis because an entity cannot be represented by just one sentiment. Several previous research stated that using LSTM-CNN got better results than using LSTM or CNN. In addition, using BERT as word embedding gets better results than using word2vec or glove. For this reason, this study aims to classify aspect-based sentiment analysis from the Bukalapak marketplace with BERT as word embedding and using the LSTM-CNN method, where LSTM is for aspect extraction and CNN for sentiment extraction. Based on testing the LSTM-CNN method, it gets better results than LSTM or CNN. The LSTM-CNN model gets an accuracy of 93.91%. Unbalanced dataset distribution can affect model performance. With the increasing number of datasets used, the accuracy of a model will increase. Classification without using stemming on datasets can increase accuracy by 2.04%.http://jurnal.iaii.or.id/index.php/RESTI/article/view/4751aspect based sentiment analysisbertcnnlstm |
| spellingShingle | Syaiful Imron Esther Irawati Setiawan Joan Santoso Mauridhi Hery Purnomo Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) aspect based sentiment analysis bert cnn lstm |
| title | Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN |
| title_full | Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN |
| title_fullStr | Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN |
| title_full_unstemmed | Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN |
| title_short | Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN |
| title_sort | aspect based sentiment analysis marketplace product reviews using bert lstm and cnn |
| topic | aspect based sentiment analysis bert cnn lstm |
| url | http://jurnal.iaii.or.id/index.php/RESTI/article/view/4751 |
| work_keys_str_mv | AT syaifulimron aspectbasedsentimentanalysismarketplaceproductreviewsusingbertlstmandcnn AT estherirawatisetiawan aspectbasedsentimentanalysismarketplaceproductreviewsusingbertlstmandcnn AT joansantoso aspectbasedsentimentanalysismarketplaceproductreviewsusingbertlstmandcnn AT mauridhiherypurnomo aspectbasedsentimentanalysismarketplaceproductreviewsusingbertlstmandcnn |