Online Reviews and Product Sales: A Sentiment Analysis Approach

Thomas, Alan (2024) Online Reviews and Product Sales: A Sentiment Analysis Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (634kB) | Preview
Preview	PDF (Configuration Manual) Download (384kB) | Preview

Abstract

Today, getting opinions of customers over the internet has become essential in understanding their buying habits and managing the profits of products. This paper seeks to discuss the impact of reviews, sympathetic, mixed or otherwise on the general public in their purchasing power. On an open dataset containing product reviews and sales, Logistic Regression, Random Forest, SVM, and XGBoost were tested, and the maximum accuracy was obtained at 86.46%. For the businesses to be able to gain something tangible from the sentiments analysis, an interface dashboard was developed to draw trends as well as the correlation between sentiments and sales. The findings unveiled a moderate positive relationship between the review sentiments, and sales trends. However, low sales sometimes came in the same periods with positive reviews, making it hard to conclude that them was an internal problem I external factors such as changes in customer demand and consumers’ preferences. As seen above, issues such as sarcasm classification and handling huge data se where addressed but are still viable prospects. The work presented here demonstrates the use of sentiment analysis and visualization techniques in strategic management and indicates some possible improvements such as the use of more complex models and integration with additional data sources. It contributes to a cumulative body of knowledge on the role that online reviews play for consumers and brings a set of useful heuristics for dealing with the effects of these reviews on sales.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nolan, Eamon 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 > 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:	05 Sep 2025 13:18
Last Modified:	05 Sep 2025 13:18
URI:	https://norma.ncirl.ie/id/eprint/8827

Actions (login required)

View Item