.png){kind=icon}
Return
An efficient model for sentiment analysis using artificial rabbits optimized vector functional link network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2023.119849.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sentiment analysis using artificial intelligence is a great tool for analyzing human linguistic capabilities. The deep learning techniques combined with Natural Language Processing (NLP) has said to offer higher performance in analyzing the sentiments in implicit aspects present in high-quality training datasets. However, the different complexities associated with deep learning techniques such as high computational and space complexity, sensitivity to learning rate, high training time, etc make them hard to implement in real-time applications. However, very few researchers have used the randomization-based neural network for sentimental analysis which offers different benefits such as increased generalization capacity, improved accuracy, low training time, and universal approximator for non-linear functions. Motivated by this problem, this paper presents an Artificial Rabbits optimized Robust Random Vector Functional Link Network (RRVFLN) for improving sentiment analysis accuracy. Initially, the data is preprocessed and the word vectors are efficiently analyzed by the Fast text method by considering each token as an n-gram character. Artificial Rabbits Optimization (ARO) is utilized to RRVFLN model's input weights and to optimize the hidden layer biases. The ARO-optimized RRVFLN model classifies the outcomes obtained in the three datasets namely the News Headline Sentiment dataset, Sentiment140 dataset, and 4000 Short Story dataset into positive and negative. The simulation results obtained by comparing the proposed model with the various existing techniques display the effectiveness in terms of F1 score, precision, classification accuracy, error rate prediction, and kappa statistics.
Keywords:
Sentiment analysis
Robust random vector functional link network
Artificial rabbits optimization
Fast text
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
Cited Papers
ShareSaveShareSaveShareSaveLatent tuberculosis infection is associated with increased unstimulated levels of interferon-gamma in Lima, Peru.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveShareSaveShort term solar power forecasting using hybrid minimum variance expanded RVFLN and Sine-Cosine Levy Flight PSO algorithmRENEWABLE ENERGY
RENEWABLE ENERGYIF9.1
PREAI
ShareSave
View more