Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network

Abstract

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.

Opinion distribution: spatial sentiment analysis of online restaurant reviews through BERT model and GIS

“…This scenario has spurred researchers to analyze online restaurant reviews from multifaceted perspectives. Notably, In Li et al [13], researchers combined Word2vec, Bi-GRU, and Attention methods to construct a sentiment analysis model for online store reviews, scrutinizing over 130,000 reviews from DianPing. Punetha and Jain [14] developed an innovative framework using unsupervised learning for sentiment analysis of TripAdvisor and Yelp restaurant reviews.…”

Improving CNN-BGRU Hybrid Network for Arabic Handwritten Text Recognition

“…LSTM neural networks limit the vanishing gradient problem by a set of 3 gates (forget gate layer, input gate layer and output gate). GRUs are like LSTMs but they only have two gates (reset gate and update gate) [30]. The reset gate determines how much information to forget and update gate defines how much information to keep.…”

“…In Fig. 2, the mechanism of GRU is presented where x t represent the input vector at time t. The previous hidden state is presented by h t−1 and the output of network is presented by h t , which is expressed by the following formulas (3)-( 6) [30]:…”

“…The weight is denoted by W , and the elementwise production is denoted by •. The BGRUs offer a mechanism to maximize the information processed [30,31]. It consists of concatenating the forward hidden layer and my backward hidden layer, which gives an output H t (formula (7)).…”

Content analysis of tripadvisor reviews on safe tourism certified restaurants during the Covid-19 pandemic

“…With increasing online activity, online reviews have become important among customers as they convey the sincere experiences and emotions of consumers (Park et al 2021). Thus, consumers who review online comments, form a general perception about the restaurant based on information shared online, which in turn influences their purchasing decisions (Li et al 2021).…”