Analyzing the Amazon Shopping Experience: A Sentiment Analysis Based on Natural Language Processing (NLP) and Model Comparison
Date
2024-05
Authors
Liang, Xiao
Major Professor
Townsend, Anthony
Advisor
Committee Member
Townsend
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Abstract
The exponential growth of e-commerce has led to an increasing reliance on online platforms for shopping, with Amazon standing at the forefront. Understanding customer sentiments expressed through product reviews on Amazon is crucial for enhancing the e-commerce experience and driving sales. This study employs sentiment analysis techniques based on natural language processing (NLP) and machine learning algorithms to analyze over 34,000 Amazon product reviews. The dataset underwent rigorous preprocessing, including data cleaning, data labeling and text cleaning. Using Logistic Regression, Random Forest, Naïve Bayes, and LSTM models to predict and classify text data with clean data. Evaluation metrics such as accuracy, precision, recall, and F1-score were utilized to compare the performance of these models.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
creative component
Comments
Rights Statement
Attribution-NonCommercial-NoDerivs 3.0 United States
Copyright
2024