Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 3

Identifikasi Kepuasan Pelanggan Minimarket Berdasarkan Ekspresi Wajah dengan Metode Convolutional Neural Network (CNN)

SemanTIK: Teknik Informasi · Vol. 12 No. 1 (2026) · pp. 157–166

DOI
10.55679/semantik.v12i1.271
ISSN
2502-8928, 2460-1446
Published
2026-06-25
Publisher
Informatics Engineering Department of Halu Oleo University
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Keberhasilan layanan minimarket tidak terlepas dari tingkat kepuasan pelanggan yang diterima selama proses pelayanan. Pengukuran kepuasan pelanggan umumnya dilakukan melalui survei atau kuesioner yang memerlukan partisipasi langsung pelanggan dan belum mampu memberikan informasi secara real-time. Penelitian ini bertujuan untuk mengidentifikasi kepuasan pelanggan berdasarkan ekspresi wajah menggunakan metode Convolutional Neural Network (CNN). Penelitian menggunakan dataset Facial Expression Recognition (FER-2013) yang dipadukan dengan data tambahan hasil pengambilan citra menggunakan webcam. Tahapan penelitian meliputi pengumpulan data, preprocessing, augmentasi data, pelatihan model CNN, dan pengujian menggunakan 20% data uji. Ekspresi wajah kemudian diklasifikasikan ke dalam kategori puas dan tidak puas. Hasil penelitian menunjukkan bahwa model CNN yang dikembangkan mampu mencapai akurasi sebesar 94% dan dapat melakukan identifikasi ekspresi wajah secara real-time. Berdasarkan hasil tersebut, metode CNN efektif digunakan untuk mengidentifikasi kepuasan pelanggan dan berpotensi mendukung evaluasi layanan yang lebih cepat, objektif, dan otomatis pada minimarket. Customer satisfaction is an important indicator in evaluating service quality in minimarkets. Conventional satisfaction measurement methods, such as surveys and questionnaires, require direct customer participation and are unable to provide real-time feedback. This study aims to identify customer satisfaction based on facial expressions using the Convolutional Neural Network (CNN) method. The study utilized the Facial Expression Recognition (FER-2013) dataset combined with additional facial image data acquired through a webcam. The research process consisted of data collection, preprocessing, data augmentation, CNN model training, and testing using 20% of the dataset. Facial expressions were then classified into satisfied and dissatisfied categories. The results showed that the proposed CNN model achieved an accuracy of 94% and was capable of recognizing facial expressions in real-time. These findings indicate that CNN is an effective approach for customer satisfaction identification and can support faster, more objective, and automated service evaluation in minimarket environments.

Keywords

Collaboration network of the authors

5 authors · 8 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Handayani Makassar
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Zahir ZainuddinUniversitas Handayani Makassar2

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://semantik.uho.ac.id/index.php/journal/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US"> Identifikasi Kepuasan Pelanggan Minimarket Berdasarkan Ekspresi Wajah dengan Metode Convolutional Neural Network (CNN) </dc:title>
	<dc:creator>Wibowo, Tanto</dc:creator>
	<dc:creator>Yuyun</dc:creator>
	<dc:creator>Hazriani</dc:creator>
	<dc:creator>Sera, Elsa</dc:creator>
	<dc:subject xml:lang="en-US">Convolutional Neural Network</dc:subject>
	<dc:subject xml:lang="en-US">Ekspresi Wajah</dc:subject>
	<dc:subject xml:lang="en-US">Kepuasan Pelanggan</dc:subject>
	<dc:description xml:lang="en-US">Keberhasilan layanan minimarket tidak terlepas dari tingkat kepuasan pelanggan yang diterima selama proses pelayanan. Pengukuran kepuasan pelanggan umumnya dilakukan melalui survei atau kuesioner yang memerlukan partisipasi langsung pelanggan dan belum mampu memberikan informasi secara real-time. Penelitian ini bertujuan untuk mengidentifikasi kepuasan pelanggan berdasarkan ekspresi wajah menggunakan metode Convolutional Neural Network (CNN). Penelitian menggunakan dataset Facial Expression Recognition (FER-2013) yang dipadukan dengan data tambahan hasil pengambilan citra menggunakan webcam. Tahapan penelitian meliputi pengumpulan data, preprocessing, augmentasi data, pelatihan model CNN, dan pengujian menggunakan 20% data uji. Ekspresi wajah kemudian diklasifikasikan ke dalam kategori puas dan tidak puas. Hasil penelitian menunjukkan bahwa model CNN yang dikembangkan mampu mencapai akurasi sebesar 94% dan dapat melakukan identifikasi ekspresi wajah secara real-time. Berdasarkan hasil tersebut, metode CNN efektif digunakan untuk mengidentifikasi kepuasan pelanggan dan berpotensi mendukung evaluasi layanan yang lebih cepat, objektif, dan otomatis pada minimarket.
Customer satisfaction is an important indicator in evaluating service quality in minimarkets. Conventional satisfaction measurement methods, such as surveys and questionnaires, require direct customer participation and are unable to provide real-time feedback. This study aims to identify customer satisfaction based on facial expressions using the Convolutional Neural Network (CNN) method. The study utilized the Facial Expression Recognition (FER-2013) dataset combined with additional facial image data acquired through a webcam. The research process consisted of data collection, preprocessing, data augmentation, CNN model training, and testing using 20% of the dataset. Facial expressions were then classified into satisfied and dissatisfied categories. The results showed that the proposed CNN model achieved an accuracy of 94% and was capable of recognizing facial expressions in real-time. These findings indicate that CNN is an effective approach for customer satisfaction identification and can support faster, more objective, and automated service evaluation in minimarket environments.</dc:description>
	<dc:publisher xml:lang="en-US">Informatics Engineering Department of Halu Oleo University</dc:publisher>
	<dc:date>2026-06-25</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://semantik.uho.ac.id/index.php/journal/article/view/271</dc:identifier>
	<dc:identifier>10.55679/semantik.v12i1.271</dc:identifier>
	<dc:source xml:lang="en-US">SemanTIK : Teknik Informasi; Vol. 12 No. 1 (2026): Vol. 12 No. 1 (2026): SemanTIK Teknik Informasi; 157-166</dc:source>
	<dc:source>2502-8928</dc:source>
	<dc:source>2460-1446</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://semantik.uho.ac.id/index.php/journal/article/view/271/70</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Tanto Wibowo, Yuyun, Hazriani, Elsa Sera</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>