Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 20;12(1):21983.
doi: 10.1038/s41598-022-26432-3.

Towards improving e-commerce customer review analysis for sentiment detection

Upendra Singh #  1 , Anant Saraswat #  1 , Hiteshwar Kumar Azad #  2 , Kumar Abhishek #  1 , S Shitharth #  3
Affiliations

Towards improving e-commerce customer review analysis for sentiment detection

Upendra Singh et al. Sci Rep. .

Abstract

According to a report published by Business Wire, the market value of e-commerce reached US$ 13 trillion and is expected to reach US$ 55.6 trillion by 2027. In this rapidly growing market, product and service reviews can influence our purchasing decisions. It is challenging to manually evaluate reviews to make decisions and examine business models. However, users can examine and automate this process with Natural Language Processing (NLP). NLP is a well-known technique for evaluating and extracting information from written or audible texts. NLP research investigates the social architecture of societies. This article analyses the Amazon dataset using various combinations of voice components and deep learning. The suggested module focuses on identifying sentences as 'Positive', 'Neutral', 'Negative', or 'Indifferent'. It analyses the data and labels the 'better' and 'worse' assumptions as positive and negative, respectively. With the expansion of the internet and e-commerce websites over the past decade, consumers now have a vast selection of products within the same domain, and NLP plays a vital part in classifying products based on evaluations. It is possible to predict sponsored and unpaid reviews using NLP with Machine Learning. This article examined various Machine Learning algorithms for predicting the sentiment of e-commerce website reviews. The automation achieves a maximum validation accuracy of 79.83% when using Fast Text as word embedding and the Multi-channel Convolution Neural Network.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Steps involved in sentiment analysis of reviews.
Figure 2
Figure 2
Bidirectional encoder representations from rransformers (BERT) representation.
Figure 3
Figure 3
BiLSTM representation.
Figure 4
Figure 4
Architecture of multi-channel CNN.
Figure 5
Figure 5
RDML architecture for classification.
Figure 6
Figure 6
BERT Plus CNN (a) BERT plus CNN accuracy curve; (b) Confusion matrix BERT plus CNN.
Figure 7
Figure 7
BERT Plus LSTM (a) Confusion matrix BERT plus LSTM; (b) BERT plus LSTM accuracy curve.
Figure 8
Figure 8
BERT Plus RMDL (a) Confusion matrix BERT plus RMDL (b) BERT plus RMDL accuracy curve.
Figure 9
Figure 9
Elmo with CNN, LSTM and RMDL (a) Confusion matrix ELMo plus CNNL; (b) Confusion matrix ELMo plus LSTM; (c) Confusion matrix ELMo plus RMDL.
Figure 10
Figure 10
Glove plus LSTM (a) Model accuracy GloVe LSTM (b) Model loss GloVe LSTM (c) Confusion matrix Glove plus LSTM.
Figure 11
Figure 11
Glove plus Multi-channel CNN and RMDL (a) Confusion matrix Glove plus Multi-channel CNN; (b) Confusion matrix Glove plus RMDL.
Figure 12
Figure 12
FastText plus LSTM and Multi-channel CNN (a) Model accuracy FastText plus LSTM (b) Model loss FastText plus LSTM (c) Confusion matrix FastText Multi-channel CNN.
Figure 13
Figure 13
FastText plus RMDL (a) Model accuracy FastText plus RMDL (b) Model loss FastText plus RMDL.
See this image and copyright information in PMC

References

    1. Azad HK, Deepak A, Chakraborty C, Abhishek K. Improving query expansion using pseudo-relevant web knowledge for information retrieval. Pattern Recogn. Lett. 2022;158:148–156. doi: 10.1016/j.patrec.2022.04.013. - DOI
    1. Azad HK, Deepak A. Query expansion techniques for information retrieval: a survey. Information Processing & Management. 2019;56(5):1698–1735. doi: 10.1016/j.ipm.2019.05.009. - DOI
    1. The Power of Reviews. 2016. Retrieved from. https://www.powerreviews.com/wp-content/uploads/2016/04/PowerofReviews_2...
    1. Kongthon, A., Sangkeettrakarn, C., Kongyoung, S. & Haruechaiyasak, C. Implementing an online help desk system based on conversational agent. In Proceedings of the International Conference on Management of Emergent Digital EcoSystems 2009 Oct 27 (pp. 450–451).
    1. Jean, S., Cho, K., Memisevic, R. & Bengio, Y. On using very large target vocabulary for neural machine translation. arXiv preprint arXiv:1412.2007. 2014 Dec 5.