Title: Border Collie optimisation algorithm for Twitter sentiment classification based on enhanced Elman spike neural network

Authors: D. Divya; Annamalai Pandiaraj; Chinnaraj Govindasamy

Addresses: Department of Computer Science and Engineering, Jerusalem College of Engineering, Chennai, India ' Department of Computing Technologies, SRM Institute of Science and Technology, Kattankulathur, Chennai, India ' Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, India

Abstract: The sentiment classification field has been increasingly interesting for academic and industrial study due to the widespread development of online reviews. Many sentiment classification approaches are developed to carry out sentiment analysis. Nevertheless, the information retrieval is not carried out precisely, is inefficient, and does not converge as quickly. To overcome these issues, an Enhanced Elman Spike Neural Network optimised with Border Collie Optimisation Algorithm for Twitter sentiment classification (EESNN-BCOA-TSC) is proposed in this paper for classifying the Twitter data. Here, the Twitter data is amassed from Twitter sentiment dataset. Then the input Twitter data is pre-processed. This pre-processed data is fed to the fast discrete curvelet transform with wrapping algorithm (FDCT-WA) for extracting the features. These extracting features are fed to EESNN-BCOA that categorises the Twitter data as positive, negative or neutral. The proposed EESNN-BCOA-TSC technique is activated in Python. From the analysis, it attains better accuracy of 99.7%, sensitivity of 98.8%, and F1-score 98.9%.

Keywords: social media; Twitter; enhanced Elman spike neural network; Border Collie optimisation algorithm; Twitter sentiment dataset.

DOI: 10.1504/IJMC.2025.145326

International Journal of Mobile Communications, 2025 Vol.25 No.3, pp.295 - 313

Received: 03 Apr 2023
Accepted: 17 Jan 2024
Published online: 31 Mar 2025 *

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