Sentiment analysis for product rating using a deep learning approach

Mohbey, Krishna Kumar

doi:10.1109/icais50930.2021.9395802

Cited by 19 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, the data from the neutral class were excluded from this study. Existing studies indicate that reviews with four-or five-star ratings out of five were considered positive, whereas those with less than three stars were considered negative [29]. Additionally, the authors removed unnecessary duplication of data.…”

Section: Data Preprocessingmentioning

confidence: 99%

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

2023

KSII TIIS

View full text Add to dashboard Cite

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…This technique implements sentimental classification on vectorized reviews through two approaches of Word2Vec, such as Skip Gram and Continuous BoGs, in 3 dissimilar vector sizes (100, 200, 300), using 2 Convolution layers and 6 BiGRU. Mohbey [15] applied NLP and ML-based approaches to SA. DL techniques such as CNN and RNN.…”

Section: Related Workmentioning

confidence: 99%

“…( 10), 𝑥 and 𝑦 indicate direction coordinates that are evaluated according to Eq. ( 11): Where 𝐴 means the angel gain [5][6][7][8][9][10][11][12][13][14][15], 𝑟 is a control gain [1,2], 𝑅 0 shows the primary value within [0.5−3], and 𝑟𝑎𝑛𝑑 denotes the randomly generated number [0,1]. This parameter helps the hawk to fly around the target with spiral movement as follows:…”

Section: Design Of Rth Optimizer For Parameter Tuningmentioning

confidence: 99%

Applied Linguistics With Red-Tailed Hawk Optimizer-Based Ensemble Learning Strategy in Natural Language Processing

Alshahrani,

Hassan,

Almalki

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Natural Language Processing (NLP) is the most vital technology in currently utilized, specifically caused by the huge and growing count of online texts that requires that understood for its massive value that completely asserted. NLP is create a sense of unstructured data, which are created by social networks and other social data sources, and is supported to organize them into an additional structured model that assists several kinds of tasks and applications. Sentiment analysis (SA), a subfield of NLP contains determining the sentiment expressed or emotional tone from a piece of text. Deep learning (DL) approaches are significantly advanced the field of SA, permitting for more accurate and nuanced classification of sentiments from the text data. In this article, we present an Advanced Sentiment Analysis using a Red-Tailed Hawk Optimizer with Ensemble Learning (ASA-RTHEL) Strategy in NLP. The aim of ASA-RTHEL technique is to exploit the strategies of ensemble learning with a hyperparameter tuning process for SA. The ASA-RTHEL technique mainly follows an ensemble learning-based classification process, which combines prediction from three DL approaches convolutional neural network (CNN), gated recurrent unit (GRU), and long short-term memory (LSTM). The ensemble process results in enhanced SA performance and decreases the risk of depending only on a single model bias or error. To boost the SA performance, the hyperparameter tuning strategy is performed by the use of the RTH algorithm. An extensive set of experiments were carried out for ensuring the superior SA results of ASA-RTHEL technique. The comprehensive comparison study highlighted the enhanced results of the MPONLP-TSA method on the recognition of various kinds of sentiments.INDEX TERMS Sentiment analysis; Natural language processing; Red-Tailed Hawk Optimizer; Deep learning; Ensemble learning.

show abstract

“…This paper's Long Short-Term Model (LSTM) prediction of the customer review's opinion has a 93.66 percent accuracy rate. Additionally, a comparison of the deep LSTM model with current models has been provided [13].…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis of Consumer Reviews Using Deep Learning

et al. 2022

View full text Add to dashboard Cite

Internet and social media platforms such as Twitter, Facebook, and several blogs provide various types of helpful information worldwide. The increased usage of social media and e-commerce websites is constantly generating a massive volume of data about image/video, sound, text, etc. The text among these is the most significant type of unstructured data, requiring special attention from researchers to acquire meaningful information. Recently, many techniques have been proposed to obtain insights from these data. However, there are still challenges in dealing with the text of enormous size; therefore, accurate polarity detection of consumer reviews is an ongoing and exciting problem. Due to this, it is challenging to derive exact meanings from the textual data from consumer reviews, comments, tweets, posts, etc. Previously, a reasonable amount of work has been conducted to simplify the extraction of exact meanings from these data. A unique technique that includes data gathering, preprocessing, feature encoding, and classification utilizing three long short-term memory variations is presented to address sentiment analysis problems. Analysing appropriate data collection, preprocessing, and classification is crucial when interpreting such data. Different textual datasets were used in the studies to gauge the importance of the suggested models. The proposed technique of predicting sentiments shows better, or at least comparable, results with less computational complexity. The outcome of this work shows the significant importance of sentiment analysis of consumer reviews and social media content to obtain meaningful insights.

show abstract

Sentiment analysis for product rating using a deep learning approach

Cited by 19 publications

References 16 publications

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

Applied Linguistics With Red-Tailed Hawk Optimizer-Based Ensemble Learning Strategy in Natural Language Processing

Sentiment Analysis of Consumer Reviews Using Deep Learning

Contact Info

Product

Resources

About