NORMA eResearch @NCI Library

Improving the Performance of Aspect Based Sentiment Analysis Using Transformer Based Techniques

Gaikar, Prathamesh (2021) Improving the Performance of Aspect Based Sentiment Analysis Using Transformer Based Techniques. 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 (1MB) | Preview

Abstract

In today’s highly competitive market, word of mouth from buyer’s viewpoint has been vital step towards success for any company. Currently, most of the enterprise in all the sectors have launched their websites to sell their products and services. Each day, millions of reviews, opinions, and sentiments are generated on the online websites regarding products and services. It is very challenging to handle and comprehend such large amount of opinion based data. Sentiment analysis is the domain which acknowledges and extracts the emotions from available opinioned data and analyze the process through natural language processing and text classification. It is the method to understand the sentiments in the text and is also becoming challenging in many research areas including the data mining field as there is a rapid increase in the number of web pages which includes product and service reviews. In this research SpaCy library is used to extract the aspect terms. For the first part of the research, transformer based models are applied without aspect based method and for the second part aspect based method is applied to same models and their results are evaluated and compared. The experiments result shows that the accuracy of transformer based models without aspect based approach is bit higher than the one with the aspect based method.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Sentiment Analysis; Natural language processing; Aspect based sentiment analysis (ABSA); Transformer based pre-trained models; text classification; XLNet; RoBERTa; ALBERT; SpaCy; Textblob
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
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 29 Nov 2021 10:57
Last Modified: 29 Nov 2021 10:57
URI: https://norma.ncirl.ie/id/eprint/5150

Actions (login required)

View Item View Item