Please use this identifier to cite or link to this item:
https://hdl.handle.net/10321/4096
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Naidoo, Shaldon Wade | en_US |
dc.contributor.author | Naicker, Nalindren | en_US |
dc.contributor.author | Patel, Sulaiman Saleem | en_US |
dc.contributor.author | Govender, Prinavin | en_US |
dc.date.accessioned | 2022-06-27T09:53:43Z | - |
dc.date.available | 2022-06-27T09:53:43Z | - |
dc.date.issued | 2022-05 | - |
dc.identifier.citation | Naidoo, S.W., Naicker, N., Patel, S.S. and Govender, P. Computer vision: the effectiveness of deep learning for emotion detection in marketing campaigns. International Journal of Advanced Computer Science and Applications. 13(5). doi:10.14569/ijacsa.2022.01305100 | en_US |
dc.identifier.issn | 2158-107X | - |
dc.identifier.issn | 2156-5570 (Online) | - |
dc.identifier.uri | https://hdl.handle.net/10321/4096 | - |
dc.description.abstract | —As businesses move towards more customer-centric business models, marketing functions are becoming increasingly interested in gathering natural, unbiased feedback from customers. This has led to increased interest in computer vision studies into emotion recognition from facial features, for application in marketing contexts. This research study was conducted using the publicly-available Facial Emotion Recognition 2013 data-set, published on Kaggle. This article provides a comparative study of four deep learning algorithms for computer vision application in emotion recognition, namely, Convolution Neural Network (CNN), Multilayer Perceptron (MLP), Recurring Neural Network (RNN), Generative Adversarial Networks (GAN) and Long Short-Term Memory (LSTM) models. Comparisons between these models were done quantitatively using the metrics of accuracy, precision, recall and f1-score; as well and qualitatively by determining goodness-of-fit and learning rate from accuracy and loss curves. The results of the study show that the CNN, GAN and MLP models surpassed the data, and the LSTM model failed to learn at all. Only the RNN adequately learnt from the data. The RNN was found to exhibit a low learning rate, and the computational intensiveness of training the model resulted in a premature termination of the training process. However, the model still achieved a test accuracy of up to 72%, the highest of all models studied, and it is possible that this could be increased through further training. The RNN also had the best F1-score (0.70), precision (0.73) and recall (0.73) of all models studied | en_US |
dc.format.extent | 8 p. | en_US |
dc.language.iso | en | en_US |
dc.publisher | The Science and Information Organization | en_US |
dc.relation.ispartof | International Journal of Advanced Computer Science and Applications; Vol. 13, Issue 5 | en_US |
dc.subject | 0803 Computer Software | en_US |
dc.subject | 1005 Communications Technologies | en_US |
dc.subject | Computer vision | en_US |
dc.subject | Deep learning | en_US |
dc.subject | Emotion detection | en_US |
dc.subject | Generative adversarial networks | en_US |
dc.subject | Marketing campaigns component | en_US |
dc.title | Computer vision: the effectiveness of deep learning for emotion detection in marketing campaigns | en_US |
dc.type | Article | en_US |
dc.date.updated | 2022-06-07T10:38:32Z | - |
dc.identifier.doi | 10.14569/ijacsa.2022.01305100 | - |
item.grantfulltext | open | - |
item.cerifentitytype | Publications | - |
item.fulltext | With Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.openairetype | Article | - |
item.languageiso639-1 | en | - |
Appears in Collections: | Research Publications (Accounting and Informatics) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Naidoo et al_2022.pdf | Article | 361.89 kB | Adobe PDF | View/Open |
IJACSA Copyright clearance.docx | Copyright clearance | 241.74 kB | Microsoft Word XML | View/Open |
Page view(s)
520
checked on Dec 22, 2024
Download(s)
288
checked on Dec 22, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.