Unfolding Customer Sentiment: A Machine Learning Approach to Sephora’s Reviews

Sonia, Vaibhav (2023) Unfolding Customer Sentiment: A Machine Learning Approach to Sephora’s Reviews. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Customer reviews are core attributes of marketing segment and product objectives. Customers express their opinions through reviews either online or in stores. The reviews which are in textual form act as an interactive window between the consumer and business. Therefore, customer reviews are analysed and processed for computation in order to understand customer-enterprise relationship. These computational entities include deploying the available data and leveraging them to derive meaningful insights which acts as a catalyst as customer understanding which leads to business expansion and betterment. In this study, the dataset consists of review windows for the cosmetic retail chain Sephora. The dataset is fetched from Kaggle which is an open-source interactive platform. The models employed for this study are linear regression, logistic regression, decision tree, support vector classification and Naive Bayes. The deployment of linear regression displays linear dependencies. On the other hand, logistic regression helps with identification of modelling binary entities which is a decision factor. Decision trees offers complex decision making into simpler comprehensive outcomes and support vector classification pioneers complex data structures and patterns. The use of Naive Bayes gives a probabilistic frameworks for the study. The models contribute to the durable analysis for different parameters. The study aims to investigate the effect of these parameters and introduce the driving factors which unfolds patterns. The experiment is performed by using Python. The resultant outcome of this study not only reflects on the impact of vivid models in exploring the distinct dynamics amongst parameters but also it serves as a directional reference for Sephora in optimizing customer benefits thereby leading towards a successful information which caters business decisions. In other aspects, the study also demonstrates the critical role that customer reviews and algorithmic methodology plays in building the success course of a cosmetic retail chain like Sephora. The inferences drawn are showcased and they display the impact of models in understanding the relationship amongst the parameters.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hafeez, Taimur UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Cosmetics Industry 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:	23 May 2025 10:54
Last Modified:	23 May 2025 10:54
URI:	https://norma.ncirl.ie/id/eprint/7619

Actions (login required)

View Item