Tools
Tools
Gautam, Akshaansh (2022) Online Review Classification using Machine Learning and Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Many online e-commerce platforms and websites that provide services online like amazon allows users to give their feedbacks for the items they have purchased. Majority of the online customers do further research about the product quality and experience before purchasing. The text data generated in the form of reviews can be analysed using sentiment analysis to obtain the sentiments of the users regarding the product and determine the fake reviews. The analysis will assist the marketers to grasp their customers preferences and prepare strategies that can satisfy the needs of customers and a well as the sellers. This report uses the best of machine learning algorithms like Logistic Regression, Decision Trees, Support Vector Machines, Naive Bayes, Random Forest, XGBoost, Extra Trees with different feature extractions like CountVectorizer and TF-IDF Vectorizer. It also uses best of Deep Learning Sequence models like LSTM, Bi-Directional LSTM, LSTM with attention layers, GRU, Bi-Directional GRU, GRU with attention layers. It can be found that the best of the models for the original dataset is Bi-Directional LSTM with 93.75% accuracy followed by Bi-Directional GRU with 93.54% accuracy. While the ReviewNet concept has achieved an accuracy of 95.57% accuracy with SVM followed by 94.40% accuracy with linear SVC. Bi-Directional LSTM and GRU have got 93.86% and 93.35% respectively. ReviewNet achieved an accuracy of 95.57% accuracy in comparison to 93.75% for the original dataset.
| Item Type: | Thesis (Masters) |
|---|---|
| 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 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: | 24 Jan 2023 16:04 |
| Last Modified: | 03 Mar 2023 12:12 |
| URI: | https://norma.ncirl.ie/id/eprint/6123 |
Actions (login required)
 |
View Item |