Article: Sentiment analysis: an empirical comparison between various training algorithms for artificial neural network Journal: International Journal of Innovative Computing and Applications (IJICA) 2020 Vol.11 No.1 pp.9 - 29 Abstract: The proliferated increase in the commercial benefits of sentiment analysis accumulated a huge interest in the domain of sentiment classification. Sentiment analysis categorises a given text into positive or negative class. In this paper, we present an empirical comparison between different training algorithms gradient descent (GD), gradient descent with momentum backpropagation (GDM), gradient descent adaptive learning rate backpropagation (GDA), gradient descent with momentum and adaptive learning rate backpropagation (GDX), and Levenberg-Marquardt backpropagation (LM), used for training the neural network for the domain of sentiment classification. The performance of all the methods is compared and evaluated using three balanced binary datasets from various domains with different features using various performance metrics such as accuracy, precision, recall, <i>f</i>-score, mean squared error, and training time. The experiments are performed five times with different random seed values using 10-fold cross-validation. The results indicate that GDX and LM outperform other methods in terms of classification accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Sentiment analysis: an empirical comparison between various training algorithms for artificial neural network

Authors: Ankit Thakkar; Dhara Mungra; Anjali Agrawal

Addresses: Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad – 382 481, Gujarat, India ' Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad – 382 481, Gujarat, India ' Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad – 382 481, Gujarat, India

Abstract: The proliferated increase in the commercial benefits of sentiment analysis accumulated a huge interest in the domain of sentiment classification. Sentiment analysis categorises a given text into positive or negative class. In this paper, we present an empirical comparison between different training algorithms gradient descent (GD), gradient descent with momentum backpropagation (GDM), gradient descent adaptive learning rate backpropagation (GDA), gradient descent with momentum and adaptive learning rate backpropagation (GDX), and Levenberg-Marquardt backpropagation (LM), used for training the neural network for the domain of sentiment classification. The performance of all the methods is compared and evaluated using three balanced binary datasets from various domains with different features using various performance metrics such as accuracy, precision, recall, f-score, mean squared error, and training time. The experiments are performed five times with different random seed values using 10-fold cross-validation. The results indicate that GDX and LM outperform other methods in terms of classification accuracy.

Keywords: sentiment analysis; artificial neural network; training algorithms; binary class; different domains.

DOI: 10.1504/IJICA.2020.105315

International Journal of Innovative Computing and Applications, 2020 Vol.11 No.1, pp.9 - 29

Received: 20 Apr 2019
Accepted: 13 May 2019
Published online: 24 Feb 2020 *

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

Title: Sentiment analysis: an empirical comparison between various training algorithms for artificial neural network

Keep up-to-date