NORMA eResearch @NCI Library

Sentiment Analysis of Customer Reviews Using Deep Learning Techniques

Chauhan, Rishabh Singh (2022) Sentiment Analysis of Customer Reviews Using Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (692kB) | Preview


The rapid increase in online shopping leads to the generation of more data like reviews, ratings, and suggestions. This data is very important for businesses to understand their customer’s sentiments and how their products are being perceived. The existing machine learning techniques and natural language processing techniques are not able to understand the context of sentences as a whole, which prevents them from providing accurate results for complex problems. Deep learning techniques are therefore required in order to classify and understand reviews more effectively and efficiently. This research has implemented four deep-learning models to analyze and evaluate the best model for sentiment analysis for customer reviews. This research has used Long Short-Term Memory, Bidirectional Recursive Neural Networks, Bidirectional Encoder Representations from Transformers, and Convolutional 1D networks. Performance metrics like Precision, Accuracy, Recall and F1 score have been used for evaluation.

Item Type: Thesis (Masters)
Milosavljevic, Vladimir
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 > Marketing > Consumer Behaviour
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: 17 May 2023 12:30
Last Modified: 17 May 2023 12:30

Actions (login required)

View Item View Item