Geodesic
Improved sentiment classification of images using a two-stage relieff and modified SCA feature selection
Nečetkie sistemy i mâgkie vyčisleniâ, Tome 19 (2024) no. 2, pp. 53-87

Voir la notice de l'article provenant de la source Math-Net.Ru

Visual media possesses rich semantics and a remarkable ability to convey emotions and sentiments. This work, aims to recognize the sentiment conveyed by the visual content of an image. This task is quite complex as it requires extracting high-level abstract content from visual data. Both global and local regions within an image carry significant emotional cues. A saliency-based approach is utilized to predict visual attention, highlighting the most crucial local areas in an image. The proposed framework consists of two main modules: (1) feature extraction from global and local image regions using a pre-trained Darknet53 CNN, which captures high-level concepts, and (2) a two-stage feature selection process using a modified Sine Cosine Algorithm (SCA) and the ReliefF algorithm, followed by classification with an SVM classifier. The proposed Modified Sine Cosine Algorithm (MSCA) enhances the search path of the original SCA by introducing a new convergence empirical parameter, preventing the algorithm from getting trapped in local optima. The experimental findings, evaluated on four datasets, demonstrate that the bi-stage feature selection combined with a deep learning approach significantly improves the accuracy of sentiment classification.
Keywords: deep learning, Darknet53, sentiment analysis, local saliency information, modified SCA, ReliefF algorithm. 
@article{FSSC_2024_19_2_a0,
     author = {K. Usha Kingsly Devi and A. Mookambiga and J. Thirumal and V. Gomathi},
     title = {Improved sentiment classification of images using a two-stage relieff and modified {SCA} feature selection},
     journal = {Ne\v{c}etkie sistemy i m\^agkie vy\v{c}isleni\^a},
     pages = {53--87},
     publisher = {mathdoc},
     volume = {19},
     number = {2},
     year = {2024},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/FSSC_2024_19_2_a0/}
}
TY  - JOUR
AU  - K. Usha Kingsly Devi
AU  - A. Mookambiga
AU  - J. Thirumal
AU  - V. Gomathi
TI  - Improved sentiment classification of images using a two-stage relieff and modified SCA feature selection
JO  - Nečetkie sistemy i mâgkie vyčisleniâ
PY  - 2024
SP  - 53
EP  - 87
VL  - 19
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/FSSC_2024_19_2_a0/
LA  - en
ID  - FSSC_2024_19_2_a0
ER  - 
%0 Journal Article
%A K. Usha Kingsly Devi
%A A. Mookambiga
%A J. Thirumal
%A V. Gomathi
%T Improved sentiment classification of images using a two-stage relieff and modified SCA feature selection
%J Nečetkie sistemy i mâgkie vyčisleniâ
%D 2024
%P 53-87
%V 19
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/FSSC_2024_19_2_a0/
%G en
%F FSSC_2024_19_2_a0
K. Usha Kingsly Devi; A. Mookambiga; J. Thirumal; V. Gomathi. Improved sentiment classification of images using a two-stage relieff and modified SCA feature selection. Nečetkie sistemy i mâgkie vyčisleniâ, Tome 19 (2024) no. 2, pp. 53-87. http://geodesic.mathdoc.fr/item/FSSC_2024_19_2_a0/