Multilingual Amazon Review Rating Classification using Bi-directional LSTM

-, Priyanka (2022) Multilingual Amazon Review Rating Classification using Bi-directional LSTM. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Today Online shopping has become an essential part of the everyone’s life. The rating of the product influences the purchasing decision of the customer. Every day, millions of the customers are posting their reviews online about the products. The posted reviews can be written in the multiple languages. Therefore, identifying the rating from the reviews becomes a tedious task. To solve such issues, we have proposed a word embedding based framework for identifying the rating from multilingual amazon review dataset. The dataset consists of the reviews in English and French language. After certain steps of data pre-processing and feature engineering, all the four models have been trained over the large subset of review data and the performance of each model has been evaluated in terms of Accuracy, PRF Score and Validation loss. After the evaluation, we have identified the better outcomes using Bi-LSTM and BERT Model.

Item Type:	Thesis (Masters)
Subjects:	P Language and Literature > PB Modern European Languages Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Customer Service H Social Sciences > HF Commerce > Electronic Commerce
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	28 Feb 2023 17:58
Last Modified:	28 Feb 2023 17:58
URI:	https://norma.ncirl.ie/id/eprint/6263

Actions (login required)

View Item