Lambhate, Atul Vasant (2022) Sentiment Analysis of Spam Reviews Using Bert-Large with SoftMax Classifier. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
The advent of the internet has made customers turn to e-commerce platforms for their shopping avenues. These e-commerce websites host a variety of products on their platform. To improve the user’s shopping experience, these platforms created a digital word-of-mouth phenomenon in the form of reviews. Customers can help make use of these reviews to facilitate their purchases whereas they can also give vital information about the product to the platform. Identifying sentiment associated with a product helps the platform maintain its image in the market as bad product reviews and customer experiences can hamper its reputation. While manual sentiment analysis is a long and tedious process for humans to perform, machines however can be made to do it without the help of human interference. This study involved implementing machine learning models to analyze the sentiments embedded in the product reviews about the musical instruments listed on the Amazon website. Three classifiers mainly Naïve Bayes, Support Vector Machines, and Long Short Term Memory Neural Networks(LSTM)are evaluated in the study using the accuracy metric. LSTM is found to be the most accurate of them all with an accuracy of 67 percentage.
Item Type: | Thesis (Masters) |
---|---|
Uncontrolled Keywords: | Sentiment Analysis; Spam Reviews; Natural Language Processing; Deep Learning |
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 > 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: | Tamara Malone |
Date Deposited: | 22 Feb 2023 15:16 |
Last Modified: | 02 Mar 2023 09:36 |
URI: | https://norma.ncirl.ie/id/eprint/6213 |
Actions (login required)
View Item |