Title: Analysis of text classification methods with large volume of tweets using deep learning

Authors: D. Hemavathi; Simbarashe Herbert Chaputsira; G. Sujatha; S. Sindhu; K. Sornalakshmi

Addresses: Faculty of School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 603203, India ' Faculty of School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 603203, India ' Faculty of School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 603203, India ' Faculty of School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 603203, India ' Faculty of School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu – 603203, India

Abstract: In day-to-day life, a large amount of data is generated by social media. Analysing the data and providing opinions about data also increased in the modern era. Sentiment Analysis plays a vibrant role in developing opinion mining systems. Much research work has been carried out in finding the important features and provides better text classification. Compared to traditional feature extraction methods, deep learning-based text feature extraction methods provide accurate text classification. This paper focused on analysing text classification using radial basis function (RBF), multilayer perceptron, and support vector machine (SVM) and improved classification accuracy. In our proposed work, an analysis has been done with the model containing the best features extracted using recurrent neural networks (RNN), long short term memory (LSTM), and autoencoder methods. 50,000 Tweets are collected from Twitter for extracting the best features related to social and political information. The improved text classification accuracy is obtained using various deep learning approaches compared to extracting the relevant features.

Keywords: text classification; RNN; recurrent neural networks; LSTM; long short term memory; RBF; radial basis function; multilayer perceptron; SVM; support vector machine.

DOI: 10.1504/IJSSE.2021.121464

International Journal of System of Systems Engineering, 2021 Vol.11 No.3/4, pp.417 - 429

Received: 10 Aug 2020
Accepted: 23 Nov 2020
Published online: 14 Mar 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article