Text classification using recurrent neural network and support vector machine on a customer review dataset

BAMGBOYE PELUMI OYELAKIN; AYODELE ADEBIYI; BABATUNDE GBADAMOSI; AROWOLO MICHEAL OLAOLU; AFOLAYAN JESUTOFUNMI; ADENIYI ABIDEMI EMMANUEL

No Detail Found!

Text classification using recurrent neural network and support vector machine on a customer review dataset

Author(s)

BAMGBOYE PELUMI OYELAKIN Depertment of computer science Landmark University, Omu-Aran, Nigeria

AYODELE ADEBIYI Depertment of computer science Landmark University, Omu-Aran, Nigeria

BABATUNDE GBADAMOSI Depertment of computer science Landmark University, Omu-Aran, Nigeria

AROWOLO MICHEAL OLAOLU Depertment of computer science Landmark University, Omu-Aran, Nigeria

AFOLAYAN JESUTOFUNMI Depertment of computer science Landmark University, Omu-Aran, Nigeria

ADENIYI ABIDEMI EMMANUEL Depertment of computer science Landmark University, Omu-Aran, Nigeria

Abstract

Text is constantly generated from our day to day use of the internet, and these large amounts of data generated are mostly unfiltered. In most cases, unstructured data needs to be classified to improve the rate at which a given text is understood. Text classification is a branch of Natural Language Processing that is used to create a distinction in unstructured text data. Machine learning is widely used in the classification of textual data as a result of its ability to create complex prediction functions dynamically. Similarly, statistical models are commonly used to classify textual data because they can describe the relationship between two or more random variables. In an e-commerce environment, sentiment analysis is usually a challenging task. Machine learning techniques of Naïve Bayes and Decision Tree have limitations in sentiment analysis performance. In this study, a comparative study of Recurrent Neural Network (RNN) and Support Vector Machine (SVM) is done for classification of customer product review dataset on whether they have positive or negative comments. This study tends to enhance the traditional RNN with the use of Long Short Term Memory (LSTM) in order to achieve optimal result. The result of this work shows that RNN with an accuracy of 94.86% is better than the state of art SVM with an accuracy of 86.67%. The result of this work is not only better in terms of accuracy, also in other performance metrics measured.

Publication Details

Page(s) 948-957

DOI DOI not available

Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 4, Year: 2022

Request the full text from PASTIC

Keywords

Support Vector Machine, Review, Text Classification, Recurrent Neural Network

Citations

Downloads

Views