Education, Science, Technology, Innovation and Life
Open Access
Sign In

Methods of Analysis of Amazon Product Reviews and Rating Prediction

Download as PDF

DOI: 10.23977/tracam.2023.030102 | Downloads: 21 | Views: 552


Shixun Huang 1, Xiaowen Zhang 2, Mingzhi Wang 3


1 Mathematical Applications in Economics and Finance, 27 King's College Cir, University of Toronto, Toronto, Canada
2 Computer Science, 27 King's College Cir, University of Toronto, Toronto, Canada
3 Computer Science and Technology, Civil Aviation Flight University of China, 46 Section 4 Nanchang Road, Guanghan, China

Corresponding Author

Shixun Huang


Online shopping reviews have become an important data source for merchants to make smarter decisions in product development, operations, and marketing. In this paper, we propose a modeling strategy to optimize data analysis and processing of online shopping review data. We address four main problems: identifying commonly used words in positive, negative, and helpful reviews, predicting the products to which the comments refer using semantic analysis, predicting the product rating based on the comments using sentiment analysis, and proposing ways to distinguish human comments from machine-generated ones. Additionally, we provide a recommendation letter to customers on how to read product reviews.


Review rating prediction, keyword extraction, sentiment analysis, TF-IDF, recurrent neural network


Shixun Huang, Xiaowen Zhang, Mingzhi Wang, Methods of Analysis of Amazon Product Reviews and Rating Prediction. Transactions on Computational and Applied Mathematics (2023) Vol. 3: 7-17. DOI:


[1] Campos, R., Mangaravite, V., Pasquali, A., Jorge, A., Nunes, C., & Jatowt, A. (2020). YAKE! Keyword extraction from single documents using multiple local features. Information Sciences, 509, 257-289.
[2] Firoozeh, N., Nazarenko, A., Alizon, F., & Daille, B. (2020). Keyword extraction: Issues and methods. Natural Language Engineering, 26(3), 259—291.
[3] Pennington, J., Socher, R., & Manning, C. (2014). GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (pp. 1532-1543).
[4] Princeton University. (2010). Retrieved from WordNet:
[5] Zhu, T. (2021). From Textual Experiments to Experimental Texts: Expressive Repetition in "Artificial Intelligence Literature". Theoretical Studies in Literature and Art, 41(5), 140—147. (n.d.). Retrieved from NLTK :: Natural Language Toolkit: 

Downloads: 111
Visits: 7557

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.