Aspect-Level Sentiment Analysis Based on Bidirectional-GRU in SIoT

Abstract

A variety of independent research activities have recently been undertaken to explore the feasibility of incorporating social networking principles into the Internet of Things solutions. The resulting model, called the Social Internet of Things, has the potential to be more powerful and competitive in supporting new IoT applications and networking services. This paper's main contribution is in sentiment analysis, which aims to predict aspect sentiments to improve the making of automated decisions and communication between associates in the social internet of things. In recent years, to analyze sentiment polarity at a subtle level, sentiment classification has become a primetime attraction. Current approaches commonly use the Long-Short Term Memory network to figure aspects and contexts separately. Usually, they perform sentiment classification using simple attention mechanisms and avoiding the bilateral information between sentences and their corresponding aspects. Therefore, the results are not satisfactory. This manuscript intends to develop a new Bidirectional gated recurrent unit model by depending on natural language processing for fully-featured mining to perform the aspect-level sentiment classification task. Our proposed model uses the Bidirectional gated recurrent unit network to acquire the dependency-based semantic analysis of sentences and their corresponding terms compared to earlier work. At the same time, it proposes a method to learn the sentiment polarity of terms in sentences. To check out our model's achievements, we perform several experiments on datasets, namely, (LAPTOP, RESTUARANT, and TWITTER). Our experiment results demonstrate that our model has achieved compelling performance and efficiency improvements in aspect sentiment classification compared with several existing models.

Stance Detection on Tweets with Multi-task Aspect-based Sentiment: A Case Study of COVID-19 Vaccination

“…Where, 𝑁𝑁 is a noun, 𝐴𝐷𝐽 is an adjective, 𝑉 is a verb, and 𝐴𝐷𝑉 is an adverb of word 𝑘 in tweet 𝑗 of user 𝑖. The result is a set of aspect term 𝐴𝑇 𝑖𝑗 = {𝑎𝑡 For aspect sentiment classification, we adopt hidden states operations [16] to enhance interaction between a context and aspect terms. The row-wise maximum and average operations were applied on tweet and aspect terms vector representation.…”

“…Existing studies have various approaches to solving subtasks of ABSA. Several studies have implemented deep learning methods for ATE and ACI tasks [14][15][16]. In another way, several rulebased methods have been developed to deal with ATE task [17][18][19][20][21], where Part of Speech (POS) Tagging and dependency parsing was executed to identify terms related to an aspect.…”

“…In another way, several rulebased methods have been developed to deal with ATE task [17][18][19][20][21], where Part of Speech (POS) Tagging and dependency parsing was executed to identify terms related to an aspect. Recently, most studies on ABSA only focused on improving the performance of ASC tasks [14][15][16][17][18][19][20][21]. Moreover, most previous ACI and ASC are two separate tasks and could not meet practical application needs [22].…”

Sentiment Analysis of Expedition Customer Satisfaction using BiGRU and BiLSTM

“…In addition to using machine learning methods, there are several studies related to sentiment analysis using deep learning methods, such as BiLSTM and BiGRU. There have been many studies on sentiment analysis regarding the methods used in sentiment analysis, such as [11], [12], and [13]. Research on the Bidirectional GRU (BiGRU) method has been carried out by [11] which discusses aspect-level sentiment analysis on SIoT to increase IoT functionality by using opinions or behavior of social media users.…”

“…There have been many studies on sentiment analysis regarding the methods used in sentiment analysis, such as [11], [12], and [13]. Research on the Bidirectional GRU (BiGRU) method has been carried out by [11] which discusses aspect-level sentiment analysis on SIoT to increase IoT functionality by using opinions or behavior of social media users. The BiGRU architecture layer (forward GRU and backward GRU) is used to obtain vectors from the input, by making the best use of the information obtained in each word.…”