Sentimental Analysis on Amazon Fine Food Reviews Using Machine Learning

Bandaru, Venkata Ramya (2023) Sentimental Analysis on Amazon Fine Food Reviews Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (901kB) | Preview

Abstract

This research project looks at sentiment analysis of amazon fine food reviews using machine learning techniques. Sorting customer reviews based on whether they are good, or negative is the main goal; this is an important process for the e-commerce industry. The paper investigates many feature extraction and data preparation techniques using logistic regression, such as Word2Vec, TF-IDF, Bag of Words, and a hybrid strategy modified with L1 regularization for better model performance. Data loading, preprocessing, model training, feature engineering, and hyperparameter tweaking are all included in the implementation step. This all-encompassing strategy guarantees the model’s efficacy in deciphering the intricate nature of human language in the reviews. Metrics including accuracy, precision, recall, F1-score, and the confusion matrix are used to assess the model’s performance. To further guarantee the robustness of the model, regularization strategies and a multicollinearity perturbation test are carried out. The outcomes demonstrate the usefulness of several feature extraction methods as well as the influence of regularization on the model. The research offers a comparative analysis that clarifies the advantages and disadvantages of each technique. In summary, the study not only shows how logistic regression can be successfully applied to sentiment analysis, but it also opens up new avenues for future research in this area. It makes a substantial contribution to sentiment analysis in e-commerce and provides a starting point for more research and advancement in this field.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HF Commerce > Electronic Commerce Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 May 2025 10:32
Last Modified:	07 May 2025 10:42
URI:	https://norma.ncirl.ie/id/eprint/7495

Actions (login required)

View Item