Analysis of text classification methods with large volume of tweets using deep learning
by D. Hemavathi; Simbarashe Herbert Chaputsira; G. Sujatha; S. Sindhu; K. Sornalakshmi
International Journal of System of Systems Engineering (IJSSE), Vol. 11, No. 3/4, 2021

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.

Online publication date: Mon, 14-Mar-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of System of Systems Engineering (IJSSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com