Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network
Today's marketing methods place a high priority on comprehending client emotions. Companies will gain insight into how customers view their goods and/or services, and they will get ideas on how to enhance their offerings. Traditional methods of sales and business are not as effective as the e-c...
| Main Author: | |
|---|---|
| Format: | Undergraduates Project Papers |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/40875/1/CB20153.pdf |
| _version_ | 1796996316765618176 |
|---|---|
| author | Muhammad Farhan Firdaus, Hairol Zaman |
| author_facet | Muhammad Farhan Firdaus, Hairol Zaman |
| author_sort | Muhammad Farhan Firdaus, Hairol Zaman |
| collection | UMP |
| description | Today's marketing methods place a high priority on comprehending client emotions. Companies will gain insight into how customers view their goods and/or services, and they will get ideas on how to enhance their offerings. Traditional methods of sales and business are not as effective as the e-commerce approach. It is such a hassle for customers to walk into the retail store and purchase their product needs. It is a waste of time and energy for today which world is full of technology. This study makes an effort to comprehend the relationship between several factors in customer reviews on an online store selling women's clothes. It also aims to categorize each review according to whether it recommends the product under consideration and whether it expresses a positive, negative, or neutral attitude. Thus, this study proposed a bidirectional recurrent neural network (RNN) with a long-short-term memory unit (LSTM) for sentiment classification. Results have indicated that a major predictor of a high sentiment score is a recommendation, and vice versa. Ratings in product reviews, on the other hand, are hazy predictors of sentiment scores. Additionally, we discovered that the bidirectional LSTM achieved an F1-score of 0.93 for sentiment classification. |
| first_indexed | 2024-04-09T03:52:33Z |
| format | Undergraduates Project Papers |
| id | UMPir40875 |
| institution | Universiti Malaysia Pahang |
| language | English |
| last_indexed | 2024-04-09T03:52:33Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | UMPir408752024-04-03T07:43:44Z http://umpir.ump.edu.my/id/eprint/40875/ Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network Muhammad Farhan Firdaus, Hairol Zaman QA75 Electronic computers. Computer science Today's marketing methods place a high priority on comprehending client emotions. Companies will gain insight into how customers view their goods and/or services, and they will get ideas on how to enhance their offerings. Traditional methods of sales and business are not as effective as the e-commerce approach. It is such a hassle for customers to walk into the retail store and purchase their product needs. It is a waste of time and energy for today which world is full of technology. This study makes an effort to comprehend the relationship between several factors in customer reviews on an online store selling women's clothes. It also aims to categorize each review according to whether it recommends the product under consideration and whether it expresses a positive, negative, or neutral attitude. Thus, this study proposed a bidirectional recurrent neural network (RNN) with a long-short-term memory unit (LSTM) for sentiment classification. Results have indicated that a major predictor of a high sentiment score is a recommendation, and vice versa. Ratings in product reviews, on the other hand, are hazy predictors of sentiment scores. Additionally, we discovered that the bidirectional LSTM achieved an F1-score of 0.93 for sentiment classification. 2023-01 Undergraduates Project Papers NonPeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/40875/1/CB20153.pdf Muhammad Farhan Firdaus, Hairol Zaman (2023) Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network. Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah. |
| spellingShingle | QA75 Electronic computers. Computer science Muhammad Farhan Firdaus, Hairol Zaman Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title | Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title_full | Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title_fullStr | Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title_full_unstemmed | Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title_short | Sentiment Analysis For E-Commerce Clothing Reviews Using Bidirectional Recurrent Neural Network |
| title_sort | sentiment analysis for e commerce clothing reviews using bidirectional recurrent neural network |
| topic | QA75 Electronic computers. Computer science |
| url | http://umpir.ump.edu.my/id/eprint/40875/1/CB20153.pdf |
| work_keys_str_mv | AT muhammadfarhanfirdaushairolzaman sentimentanalysisforecommerceclothingreviewsusingbidirectionalrecurrentneuralnetwork |