Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network
In the era of Web 2.0, there is a huge amount of user-generated content, but the huge amount of unstructured data makes it difficult for merchants to provide personalized services and for users to extract information efficiently, so it is necessary to perform sentiment analysis for restaurant review...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/8/1517 |
id |
doaj-756b667ce8b54f4f8156e9d195f0cb87 |
---|---|
record_format |
Article |
spelling |
doaj-756b667ce8b54f4f8156e9d195f0cb872021-08-26T14:24:20ZengMDPI AGSymmetry2073-89942021-08-01131517151710.3390/sym13081517Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural NetworkLiangqiang Li0Liang Yang1Yuyang Zeng2Business and Tourism School, Sichuan Agricultural University, Chengdu 611830, ChinaBusiness and Tourism School, Sichuan Agricultural University, Chengdu 611830, ChinaBusiness and Tourism School, Sichuan Agricultural University, Chengdu 611830, ChinaIn the era of Web 2.0, there is a huge amount of user-generated content, but the huge amount of unstructured data makes it difficult for merchants to provide personalized services and for users to extract information efficiently, so it is necessary to perform sentiment analysis for restaurant reviews. The significant advantage of Bi-GRU is the guaranteed symmetry of the hidden layer weight update, to take into account the context in online restaurant reviews and to obtain better results with fewer parameters, so we combined Word2vec, Bi-GRU, and Attention method to build a sentiment analysis model for online restaurant reviews. Restaurant reviews from Dianping.com were used to train and validate the model. With F1-score greater than 89%, we can conclude that the comprehensive performance of the Word2vec+Bi-GRU+Attention sentiment analysis model is better than the commonly used sentiment analysis models. We applied deep learning methods to review sentiment analysis in online food ordering platforms to improve the performance of sentiment analysis in the restaurant review domain.https://www.mdpi.com/2073-8994/13/8/1517online restaurant reviewsBi-GRUsentiment analysisattention |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liangqiang Li Liang Yang Yuyang Zeng |
spellingShingle |
Liangqiang Li Liang Yang Yuyang Zeng Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network Symmetry online restaurant reviews Bi-GRU sentiment analysis attention |
author_facet |
Liangqiang Li Liang Yang Yuyang Zeng |
author_sort |
Liangqiang Li |
title |
Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network |
title_short |
Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network |
title_full |
Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network |
title_fullStr |
Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network |
title_full_unstemmed |
Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network |
title_sort |
improving sentiment classification of restaurant reviews with attention-based bi-gru neural network |
publisher |
MDPI AG |
series |
Symmetry |
issn |
2073-8994 |
publishDate |
2021-08-01 |
description |
In the era of Web 2.0, there is a huge amount of user-generated content, but the huge amount of unstructured data makes it difficult for merchants to provide personalized services and for users to extract information efficiently, so it is necessary to perform sentiment analysis for restaurant reviews. The significant advantage of Bi-GRU is the guaranteed symmetry of the hidden layer weight update, to take into account the context in online restaurant reviews and to obtain better results with fewer parameters, so we combined Word2vec, Bi-GRU, and Attention method to build a sentiment analysis model for online restaurant reviews. Restaurant reviews from Dianping.com were used to train and validate the model. With F1-score greater than 89%, we can conclude that the comprehensive performance of the Word2vec+Bi-GRU+Attention sentiment analysis model is better than the commonly used sentiment analysis models. We applied deep learning methods to review sentiment analysis in online food ordering platforms to improve the performance of sentiment analysis in the restaurant review domain. |
topic |
online restaurant reviews Bi-GRU sentiment analysis attention |
url |
https://www.mdpi.com/2073-8994/13/8/1517 |
work_keys_str_mv |
AT liangqiangli improvingsentimentclassificationofrestaurantreviewswithattentionbasedbigruneuralnetwork AT liangyang improvingsentimentclassificationofrestaurantreviewswithattentionbasedbigruneuralnetwork AT yuyangzeng improvingsentimentclassificationofrestaurantreviewswithattentionbasedbigruneuralnetwork |
_version_ |
1721189598417125376 |