Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model
Abstract Users of e‐commerce websites review different aspects of a product in the comment section. In this research, an approach is proposed for opinion aspect extraction and recognition in selling systems. We have used the users' opinions from the Digikala website (www.Digikala.com), which is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-09-01
|
| Series: | Applied AI Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ail2.86 |
| _version_ | 1797693898373464064 |
|---|---|
| author | Kamal Sharbatian Mohammad Hossein Moattar |
| author_facet | Kamal Sharbatian Mohammad Hossein Moattar |
| author_sort | Kamal Sharbatian |
| collection | DOAJ |
| description | Abstract Users of e‐commerce websites review different aspects of a product in the comment section. In this research, an approach is proposed for opinion aspect extraction and recognition in selling systems. We have used the users' opinions from the Digikala website (www.Digikala.com), which is an Iranian e‐commerce company. In this research, a language‐independent framework is proposed that is adjustable to other languages. In this regard, after necessary text processing and preparation steps, the existence of an aspect in an opinion is determined using deep learning algorithms. The proposed model combines Convolutional Neural Network (CNN) and long‐short‐term memory (LSTM) deep learning approaches. CNN is one of the best algorithms for extracting latent features from data. On the other hand, LSTM can detect latent temporal relationships among different words in a text due to its memory ability and attention model. The approach is evaluated on six classes of opinion aspects. Based on the experiments, the proposed model's accuracy, precision, and recall are 70%, 60%, and 85%, respectively. The proposed model was compared in terms of the above criteria with CNN, Naive Bayes, and SVM algorithms and showed satisfying performance. |
| first_indexed | 2024-03-12T02:50:19Z |
| format | Article |
| id | doaj.art-6daf44d1efbc4c8c815a932103369c37 |
| institution | Directory Open Access Journal |
| issn | 2689-5595 |
| language | English |
| last_indexed | 2024-03-12T02:50:19Z |
| publishDate | 2023-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied AI Letters |
| spelling | doaj.art-6daf44d1efbc4c8c815a932103369c372023-09-04T05:10:41ZengWileyApplied AI Letters2689-55952023-09-0143n/an/a10.1002/ail2.86Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention modelKamal Sharbatian0Mohammad Hossein Moattar1Department of Computer Engineering Urmia University of Technology Urmia IranDepartment of Computer Engineering, Mashhad Branch Islamic Azad University Mashhad IranAbstract Users of e‐commerce websites review different aspects of a product in the comment section. In this research, an approach is proposed for opinion aspect extraction and recognition in selling systems. We have used the users' opinions from the Digikala website (www.Digikala.com), which is an Iranian e‐commerce company. In this research, a language‐independent framework is proposed that is adjustable to other languages. In this regard, after necessary text processing and preparation steps, the existence of an aspect in an opinion is determined using deep learning algorithms. The proposed model combines Convolutional Neural Network (CNN) and long‐short‐term memory (LSTM) deep learning approaches. CNN is one of the best algorithms for extracting latent features from data. On the other hand, LSTM can detect latent temporal relationships among different words in a text due to its memory ability and attention model. The approach is evaluated on six classes of opinion aspects. Based on the experiments, the proposed model's accuracy, precision, and recall are 70%, 60%, and 85%, respectively. The proposed model was compared in terms of the above criteria with CNN, Naive Bayes, and SVM algorithms and showed satisfying performance.https://doi.org/10.1002/ail2.86aspect classificationconvolutional neural networkdeep learninglong short‐term memoryopinion mining |
| spellingShingle | Kamal Sharbatian Mohammad Hossein Moattar Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model Applied AI Letters aspect classification convolutional neural network deep learning long short‐term memory opinion mining |
| title | Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| title_full | Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| title_fullStr | Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| title_full_unstemmed | Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| title_short | Deep aspect extraction and classification for opinion mining in e‐commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| title_sort | deep aspect extraction and classification for opinion mining in e commerce applications using convolutional neural network feature extraction followed by long short term memory attention model |
| topic | aspect classification convolutional neural network deep learning long short‐term memory opinion mining |
| url | https://doi.org/10.1002/ail2.86 |
| work_keys_str_mv | AT kamalsharbatian deepaspectextractionandclassificationforopinionmininginecommerceapplicationsusingconvolutionalneuralnetworkfeatureextractionfollowedbylongshorttermmemoryattentionmodel AT mohammadhosseinmoattar deepaspectextractionandclassificationforopinionmininginecommerceapplicationsusingconvolutionalneuralnetworkfeatureextractionfollowedbylongshorttermmemoryattentionmodel |