CBVoSD: context based vectors over sentiment domain ensemble model for review classification

Wankhade, Mayur; Annavarapu, Chandra Sekhara Rao; Verma, Mukul Kirti

doi:10.1007/s11227-021-04132-5

Cited by 17 publications

(4 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The scientific community interest in sentiment analysis is increasing because it facilitates decision-making for a variety of applications that rely on community opinion. As a result, previous studies various automated techniques for sentiment analysis 7 . In investigated customized methods to identify constructs such as dominant behavior in electronic chats have and have demonstrated the potential to enhance analysis by expediting automated sentiment categorization utilizing NLP techniques 8 .…”

Section: Related Workmentioning

confidence: 99%

Opinion analysis and aspect understanding during covid-19 pandemic using BERT-Bi-LSTM ensemble method

Wankhade

Rao

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Social media platforms significantly increase general information about disease severity and inform preventive measures among community members. To identify public opinion through tweets on the subject of Covid-19 and investigate public sentiment in the country over the period. This article proposed a novel method for sentiment analysis of coronavirus-related tweets using bidirectional encoder representations from transformers (BERT) bi-directional long short-term memory (Bi-LSTM) ensemble learning model. The proposed approach consists of two stages. In the first stage, the BERT model gains the domain knowledge with Covid-19 data and fine-tunes with sentiment word dictionary. The second stage is the Bi-LSTM model, which is used to process the data in a bi-directional way with context sequence dependency preserving to process the data and classify the sentiment. Finally, the ensemble technique combines both models to classify the sentiment into positive and negative categories. The result obtained by the proposed method is better than the state-of-the-art methods. Moreover, the proposed model efficiently understands the public opinion on the Twitter platform, which can aid in formulating, monitoring and regulating public health policies during a pandemic.

show abstract

Section: Related Workmentioning

confidence: 99%

Opinion analysis and aspect understanding during covid-19 pandemic using BERT-Bi-LSTM ensemble method

Wankhade

Rao

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the SA scope of work, the sentimental polarity of words is inherently dependent on the domain [ 3 ]. For instance, the adjective “unpredictable” has negative polarity in the phrase “unpredictable steering” in a car review text but a positive polarity in the phrase “unpredictable plot” in a movie review sentence.…”

Section: Introductionmentioning

confidence: 99%

Topic sentiment analysis based on deep neural network using document embedding technique

2023

View full text Add to dashboard Cite

Sentiment Analysis (SA) is a domain- or topic-dependent task since polarity terms convey different sentiments in various domains. Hence, machine learning models trained on a specific domain cannot be employed in other domains, and existing domain-independent lexicons cannot correctly recognize the polarity of domain-specific polarity terms. Conventional approaches of Topic Sentiment Analysis perform Topic Modeling (TM) and SA sequentially, utilizing the previously trained models on irrelevant datasets for classifying sentiments that cannot provide acceptable accuracy. However, some researchers perform TM and SA simultaneously using topic-sentiment joint models, which require a list of seeds and their sentiments from widely used domain-independent lexicons. As a result, these methods cannot find the polarity of domain-specific terms correctly. This paper proposes a novel supervised hybrid TSA approach, called Embedding Topic Sentiment Analysis using Deep Neural Networks (ETSANet), that extracts the semantic relationships between the hidden topics and the training dataset using Semantically Topic-Related Documents Finder (STRDF). STRDF discovers those training documents in the same context as the topic based on the semantic relationships between the Semantic Topic Vector, a newly introduced concept that encompasses the semantic aspects of a topic, and the training dataset. Then, a hybrid CNN–GRU model is trained by these semantically topic-related documents. Moreover, a hybrid metaheuristic method utilizing Grey Wolf Optimization and Whale Optimization Algorithm is employed to fine-tune the hyperparameters of the CNN–GRU network. The evaluation results demonstrate that ETSANet increases the accuracy of the state-of-the-art methods by 1.92%.

show abstract

“…Luo Y and others provided help by analyzing the additional commodity comments of the cross-border pharmaceutical platform, which will increase sales [6] . In order to improve the reputation of merchants, Wankhade M et al proposed a new vector algorithm in the emotional field, thereby improving the effect of emotional classification of comments [7] . Under this background, in order to better analyze the sentiment of e-commerce product reviews and solve many problems, the research proposes a deep learning algorithm (Bidirectional Encoder Representations from Transformers Bidirectional and Gated Current Unit, Bert BiGRU) that combines bidirectional encoder representation of transformers with bidirectional gating cycle unit, The purpose of this algorithm is to quickly and effectively extract the emotional tendencies in product reviews, so as to provide help for businesses to improve products and quality inspection departments to solve problems related to the quality of e-commerce products.…”

Section: Introductionmentioning

confidence: 99%

Research on emotion analysis of e-commerce product reviews based on deep learning

Duan¹,

Jiang²,

Erlin³

2023

Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022)

View full text Add to dashboard Cite

The rapid development of e-commerce has prompted the emergence of massive product reviews. Quickly grasping the emotional tendencies in e-commerce product reviews has become an effective way for businesses to improve their problems. Therefore, based on Bert and GUP, the research proposes Bert BiGRU deep learning algorithm, and verifies its effectiveness in the emotional analysis of e-commerce product reviews. The experimental results show that Bert BiGRU algorithm has the highest accuracy of 95.51% among the seven algorithms. In addition, Bert BiGRU algorithm has achieved good training effect after only eight times of training. In addition, Bert BiGRU algorithm has been used in practice to analyze the emotional tendencies in four mobile phone reviews, which shows high reliability. In a word, Bert BiGRU algorithm has high performance and low cost. It has high practicability in the emotional analysis of e-commerce product reviews.

show abstract

CBVoSD: context based vectors over sentiment domain ensemble model for review classification

Cited by 17 publications

References 73 publications

Opinion analysis and aspect understanding during covid-19 pandemic using BERT-Bi-LSTM ensemble method

Opinion analysis and aspect understanding during covid-19 pandemic using BERT-Bi-LSTM ensemble method

Topic sentiment analysis based on deep neural network using document embedding technique

Research on emotion analysis of e-commerce product reviews based on deep learning

Contact Info

Product

Resources

About