Text sentiment classification of Amazon reviews using word embeddings and convolutional neural networks

Qorich, Mohammed; Ouazzani, Rajae El

doi:10.1007/s11227-023-05094-6

Cited by 17 publications

(35 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…K. S. Kumar et al [15] mined Amazon reviews for three products, namely, the Apple iPhone 5S, Samsung J7, and Redmi Note 3, employing ML models and discovering that Naïve Bayes (NB) outperformed LR in categorizing reviews as positive or negative, evaluated through recall, precision, and F-measure. M. Qorich et al [16] tackled text sentiment analysis on Amazon reviews by combining word embeddings with CNNs. Their study utilized two-word embedding techniques, namely, FastText [17] and Word2Vec, and applied these to three different datasets.…”

Section: Related Workmentioning

confidence: 99%

“…However, upon implementing our proposed BERT model on their entire dataset, we realized a substantial improvement, with an impressive accuracy score of 93.7% and an F1 score of 93%, significantly surpassing the baseline. Qorich et al [16] focused on a dataset centered around Amazon reviews, encompassing a substantial 400,00 records. Their rigorous testing leads up to a commendable peak accuracy of 90%.…”

Section: Comparison Of the Proposed Approach With The State-of-the-artmentioning

confidence: 99%

“…Proposed Work Accuracy [23] Consumer Reviews of Amazon Products 71.5% 93.7% [16] Amazon Reviews for Sentiment Analysis 90% 91% [46] Amazon Mobile Phone Reviews 94% 90% [47] Amazon Fine Food Reviews 88% 86%…”

Section: Ref Dataset Name Baseline Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Analyzing Amazon Products Sentiment: A Comparative Study of Machine and Deep Learning, and Transformer-Based Techniques

Ali,

Hashmi,

Yayilgan Yildirim

et al. 2024

Electronics

View full text Add to dashboard Cite

In recent years, online shopping has surged in popularity, with customer reviews becoming a crucial aspect of the decision-making process. Reviews not only help potential customers make informed choices, but also provide businesses with valuable feedback and build trust. In this study, we conducted a thorough analysis of the Amazon reviews dataset, which includes several product categories. Our primary objective was to accurately classify sentiments using natural language processing, machine learning, ensemble learning, and deep learning techniques. Our research workflow encompassed several crucial steps. We explore data collection procedures; preprocessing steps, including normalization and tokenization; and feature extraction, utilizing the Bag-of-Words and TF–IDF methods. We conducted experiments employing a variety of machine learning algorithms, including Multinomial Naive Bayes, Random Forest, Decision Tree, and Logistic Regression. Additionally, we harnessed Bagging as an ensemble learning technique. Furthermore, we explored deep learning-based algorithms, such as CNNs, Bidirectional LSTM, and transformer-based models, like XLNet and BERT. Our comprehensive evaluations, utilizing metrics such as accuracy, precision, recall, and F1 score, revealed that the BERT algorithm outperformed others, achieving an impressive accuracy rate of 89%. This research provides valuable insights into the sentiment analysis of Amazon reviews, aiding both consumers and businesses in making informed decisions and enhancing product and service quality.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Comparison Of the Proposed Approach With The State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

Analyzing Amazon Products Sentiment: A Comparative Study of Machine and Deep Learning, and Transformer-Based Techniques

Ali,

Hashmi,

Yayilgan Yildirim

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…A convolutional neural network (CNN) model for negative/positive sentiment classification in text reviews has been provided by Qorich & El Ouazzani [21]. To find the best model, we also compared our suggested CNN model with other models' word embedding representations.…”

Section: Related Workmentioning

confidence: 99%

Analyzing Public Sentiment on the Amazon Website: A GSK-Based Double Path Transformer Network Approach for Sentiment Analysis

Kumar,

Thatha,

Udayaraju

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Sentiment Analysis (SA) holds considerable significance in comprehending public perspectives and conducting precise opinion-based evaluations, making it a prominent theme in natural language processing research. With the increasing trend of online shopping and social media usage, there is a constant influx of diverse data types such as images, videos, audio, and text. Notably, text stands out as the most crucial form of unstructured data, demanding heightened attention from researchers. Given the voluminous nature of data, various methodologies have been proposed to effectively mine big datasets for valuable insights. The challenge of accurately identifying polarity in extensive customer evaluations persists due to the intricacies associated with handling large textual datasets derived from reviews, comments, tweets, and posts. This study addresses this challenge by presenting a straightforward architecture, the Double Path Transformer Network (DPTN), designed to model both global and local information for comprehensive review categorization. To enhance the synergy between the attention path and the convolutional path, the study advocates a parallel design that combines a robust self-attention mechanism with a convolutional network. The research employs the gaining-sharing knowledge optimization (GSK) approach to fine-tune hyperparameters, thereby improving the model's classification accuracy. Additionally, the investigation demonstrates that optimization algorithms and deep learning collaboratively manage class imbalances with finesse, even in the absence of explicit measures for such concerns. In the experiment analysis of the proposed model ultimately achieved an accuracy of 95.

show abstract

“…Jiang get better results by using the optimized support vector machine and quantile regression to carry out interval prediction of tourism demand after identifying key variables such as online search keywords and environmental factors [19]. Kurich et al realized that social text and online consumer reviews can re ect consumers' emotional states, and text classi cation algorithms can be used to label customers' negative or positive emotions, which can reveal consumers' preferences [20]. Therefore, in addition to the search index, online comments shared by consumers on travel websites also play a potential role in predicting tourists' travel behavior.…”

Section: 1tourist Ow Prediction Based On Internet Big Datamentioning

confidence: 99%

A Multi-scale Combined Prediction on Tourist Flow: Does Internet Big Data Matter？

Liu,

Zhao,

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

This article proposes a multi-scale combination prediction method for tourism traffic driven by internet big data. Firstly, process data on tourist traffic, Baidu index, and online reviews. Use Principal Component Analysis (PCA) to reduce the dimensionality of Baidu Index, and then use Snownlp to calculate the emotional value of each online comment. Secondly, a mixed multi-scale decomposition method is used to decompose tourism traffic and processed data, and sample entropy is used to reconstruct the decomposition results into high-frequency, low-frequency, and trend components. Thirdly, LSTM, BPNN, and SVR are used to predict high-frequency, low-frequency, and trend components, respectively, to obtain the predicted values under the three decomposition paths. The optimal weighted combination is used to obtain the final prediction result. Finally, the empirical analysis of tourism flow in Jiuzhaigou Valley,the result shows that the Internet big data can significantly improve the prediction effect of tourism flow.

show abstract

Text sentiment classification of Amazon reviews using word embeddings and convolutional neural networks

Cited by 17 publications

References 51 publications

Analyzing Amazon Products Sentiment: A Comparative Study of Machine and Deep Learning, and Transformer-Based Techniques

Analyzing Amazon Products Sentiment: A Comparative Study of Machine and Deep Learning, and Transformer-Based Techniques

Analyzing Public Sentiment on the Amazon Website: A GSK-Based Double Path Transformer Network Approach for Sentiment Analysis

A Multi-scale Combined Prediction on Tourist Flow: Does Internet Big Data Matter？

Contact Info

Product

Resources

About