E-Shopping Website Performance Analysis and Prediction Review using Sentiment Analysis

S. Jeba Shiny*
Department of Computer Science and Engineering, DMI Engineering College, Aralvaimozhi, Tamil Nadu, India.
Periodicity:June - August'2021
DOI : https://doi.org/10.26634/jcom.9.2.18430

Abstract

In today's world, internet evaluations are critical in influencing customer purchasing habits and improving worldwide communications among consumers. Internet giants like Amazon and Flipkart provide customers an opportunity to share their experiences and thoughts about the product's performance with respective customers. Classification of reviews into positive and negative sentiment is needed in order to obtain useful information from a huge number of reviews. When it comes to extracting subjective information from texts, Sentiment Analysis utilises computer algorithms. One of the most important NLP (Natural Language Processing) jobs is sentiment analysis, often known as opinion mining. The field of sentiment analysis have got attraction. It is one of the basic issues of sentiment analysis to solve the problem of sentiment polarity classification. A generic sentiment polarity classification method is provided along with comprehensive process explanations. This study's data comes from online product evaluations gained from sites like Amazon, Flipkart, eBay, and others that influence online shoppers. Text processing methods were used to preprocess customer evaluations of products. The Product review files are produced as a flat-file during pre-processing. After eliminating the stop words, the flat file is tokenized and the keywords are listed. Each word's frequency has been determined, and the subject with the greatest frequency count has been extracted. Similar comments are grouped together in each subject, and the resulting words are then categorised as either positive or negative. For ease of understanding, a chart is created from the categorised comments. Nave Bayes, Support Vector Machine (SVM), Decision Tree, and k-Nearest Neighbor are just a few of the classification models that have been used to classify user evaluations. Models are evaluated by utilising 10-Fold Cross Validation (FCV).

Keywords

Sentimental Analysis, Fold Cross Validation (FCV), Support Vector Machine, Natural Language Processing (NLP), Decision Tree.

How to Cite this Article?

Jeba Shiny, S. (2021). E-Shopping Website Performance Analysis and Prediction Review Using Sentiment Analysis. i-manager's Journal on Computer Science, 9(2), 10-21. https://doi.org/10.26634/jcom.9.2.18430

References

[4]. Huq, M. R., Ali, A., & Rahman, A. (2017). Sentiment analysis on Twitter data using KNN and SVM. International Journal of Advanced Computer Science and Applications, 8(6), 19-25.
[6]. Mate, C. (2015). Product aspect ranking using sentiment analysis: a survey. International Research Journal of Engineering and Technology, 3(01), 126-127.
[7]. Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, (2 (1-2)), 1-135.
[8]. Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. Proceedings of EMNLP, 2002. Introduced polarity dataset v0.9.
[10]. Popescu, A. M., Nguyen, B., & Etzioni, O. (2005). OPINE: Extracting product features and opinions from reviews. In Proceedings of HLT/EMNLP on Interactive Demonstrations(pp.32-33).
[12]. Wang, J., Zhao, J., Guo, S., North, C., & Ramakrishnan, N. (2020). ReCloud: semantics-based word cloud visualization of user reviews. In Graphics Interface 2014 (pp. 151-158). AK Peters/CRC Press.
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.