NORMA eResearch @NCI Library

Sentiment Analysis of Customer Reviews on Amazon Electronics Product: Natural Language Processing Approach and Machine Learning

Yadav, Vipin (2022) Sentiment Analysis of Customer Reviews on Amazon Electronics Product: Natural Language Processing Approach and Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

There is a rapid rise in online shopping over the last few decades, people tend to buy things online rather than going to shop. E-commerce companies like Amazon, Flipkart, eBay are funding more innovative projects related to customers data. It’s been estimated that Amazon’s retail business tripled from last year. Most the eCommerce site seeks Customer’ review and rating for their product. This practice of providing feedback is helpful for other customers and for the business too.Product feedback from the consumer will be helpful for another customer to get more insight into the product during their purchases, as well as for the eCommerce company that helps to know the quality and uses of their products and utilizes that feedback for improving their products. This paper aims to analyze the sentiments of customer’s feedback against Amazon’s product. Data will be imported from web sources for further analysis. As text data is always in an impure form, so data cleaning and pre-processing must be done. Natural language processing toolkit is one of the techniques that will be used for pre processing data by removing stop words, nouns, pronouns, punctuation marks, and for the bag of words, the vectorization technique of NLP will be implemented. Customer’s sentiments in their feedback will be categorized by labeling the data into three categories Positive, negative, and neutral. For further analysis on the cleaned and labeled data, machine learning models, the hybrid method will be used in which two or three algorithms of ML will be evaluated and compared with another algorithm of ML.

Item Type: Thesis (Masters)
Uncontrolled Keywords: NLP; sentiment analysis; machine learning; MNB; MLP; SGD classifier; count-vector; TD-IDF
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Cloud computing
H Social Sciences > HF Commerce > Electronic Commerce
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Tamara Malone
Date Deposited: 30 Nov 2022 14:56
Last Modified: 06 Dec 2022 18:14
URI: https://norma.ncirl.ie/id/eprint/5946

Actions (login required)

View Item View Item