NORMA eResearch @NCI Library

Fined-Grained Sentiment Analysis of Yelp Reviews Using Deep Learning Models

Browne, Aidan (2020) Fined-Grained Sentiment Analysis of Yelp Reviews Using Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (14MB) | Preview

Abstract

With the development of Web 2.0 capabilities in the early 1990’s the way we as human beings interact with each other changed forever. From that period user generated content via social media platforms saw an exponential increase in popularity. Websites such as Yelp became the new place where people discussed how they felt about a business’s product or service. Due to this shift businesses more than ever need to understand how the public feel about their product. As part of this project 6 deep learning models were used to make a fine-grained sentiment analysis on the Yelp Open Dataset. In addition to applying sentiment analysis this project attempted to answer if it was possible to increase sentiment accuracy score by selecting reviews considered useful by the public. The models deployed were based on a new technique for Natural Language Processing developed by Google in 2018. With an overall accuracy score an algorithm based on Google’s A Light BERT model achieved the best result of 68.39%

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 18 Jan 2021 13:29
Last Modified: 18 Jan 2021 13:29
URI: https://norma.ncirl.ie/id/eprint/4363

Actions (login required)

View Item View Item