Perancangan Sistem Pendeteksi Emosional Siswa Menggunakan Algoritma CNN untuk Mengukur Tingkat Pengelolaan Kelas
DOI:
https://doi.org/10.57255/intellect.v3i02.295Keywords:
Emosional, Pengelolaan Kelas, CNNAbstract
This Papers is motivated by a problem at SMAN 5 Bukittinggi shows that teachers often have difficulty analyzing the emotional state of their students. This is based on the difficulty of teachers to control and classify the emotional state of each student while learning, which has an impact on the effectiveness of classroom management. The developed system is designed to automatically detect students' emotions, so that teachers can understand students' emotional conditions and adjust teaching methods. The research method used is Research and Development (R&D) which includes the stages of needs identification, design, development, testing, implementation, and evaluation. The data used are 28,700 facial images taken from the Kaggle platform and used to train CNN models in classifying seven emotions: angry, disgusted, afraid, happy, sad, surprised, and neutral. The system was tested at SMA Negeri 5 Bukittinggi involving teachers and students. The results showed that the developed system was valid (score 0.88), practical (score 0.62), and effective (score 0.83) in detecting students' emotions and helping classroom management. The contributions of this research include innovating the use of AI in education, providing technological solutions for teachers to better understand students' emotional states, and improving the interaction and quality of classroom management. Overall, the system is expected to help improve the quality of learning by providing teachers with more sophisticated and responsive tools to support effective classroom management.
Abstrak
Artikel ini dilatar belakangi dari suatu permasalahan di SMAN 5 Bukittinggi menunjukkan bahwa guru sering mengalami kesulitan mengenai analisa emosional dari siswanya. ini didasari oleh guru susah untuk mengontrol dan mengklasisifikasikan emosional dari setiap siswa saat belajar, yang berdampak pada efektivitas pengelolaan kelas. Sistem yang dikembangkan dirancang untuk mendeteksi emosi siswa secara otomatis, sehingga guru dapat memahami kondisi emosional siswa dan menyesuaikan metode pengajaran. Metode penelitian yang digunakan adalah Research and Development (R&D) yang meliputi tahapan identifikasi kebutuhan, desain, pengembangan, pengujian, implementasi, dan evaluasi. Data yang digunakan berupa 28.700 citra wajah yang diambil dari platform Kaggle dan digunakan untuk melatih model CNN dalam mengklasifikasikan tujuh emosi: marah, jijik, takut, senang, sedih, terkejut, dan netral. Sistem diuji di SMA Negeri 5 Bukittinggi dengan melibatkan guru dan siswa. Hasil penelitian menunjukkan bahwa sistem yang dikembangkan valid (skor 0,88), praktis (skor 0,62), dan efektif (skor 0,83) dalam mendeteksi emosi siswa dan membantu pengelolaan kelas. Kontribusi penelitian ini mencakup inovasi penggunaan AI dalam pendidikan, memberikan solusi teknologi bagi guru untuk lebih memahami kondisi emosional siswa, serta meningkatkan interaksi dan kualitas pengelolaan kelas. Secara keseluruhan, sistem ini diharapkan dapat membantu meningkatkan kualitas pembelajaran dengan memberikan guru alat yang lebih canggih dan responsif untuk mendukung pengelolaan kelas yang efektif.
Downloads
References
N. Agustian and U. H. Salsabila, “Peran Teknologi Pendidikan dalam Pembelajaran,” Islamika, vol. 3, no. 1, pp. 123–133, 2021, doi: 10.36088/islamika.v3i1.1047.
Y. Shou, T. Meng, W. Ai, S. Yang, and K. Li, “Conversational emotion recognition studies based on graph convolutional neural networks and a dependent syntactic analysis,” Neurocomputing, 2022, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0925231222008001
P. A. Nugroho, I. Fenriana, and R. Arijanto, “Implementasi Deep Learning Menggunakan Convolutional Neural Network ( Cnn ) Pada Ekspresi Manusia,” Algor, vol. 2, no. 1, pp. 12–21, 2020.
A. S. Alluhaidan, O. Saidani, R. Jahangir, M. A. Nauman, and ..., “Speech emotion recognition through hybrid features and convolutional neural network,” Applied Sciences. mdpi.com, 2023. [Online]. Available: https://www.mdpi.com/2076-3417/13/8/4750
Y. Nam and C. Lee, “Cascaded convolutional neural network architecture for speech emotion recognition in noisy conditions,” Sensors. mdpi.com, 2021. [Online]. Available: https://www.mdpi.com/1424-8220/21/13/4399
S. S. Ripan Septian, Dede Irawan Saputra, “Klasifikasi Emosi Menggunakan Convolutional Neural Networks Emotion,” in SENTER 2019: Seminar Nasional Teknik Elektro 2019, 2019, pp. 53–62. doi: 10.13733/j.jcam.issn.2095-5553.2022.11.026.
A. Werdayanti and L. Belakang, “Pengaruh Kompetensi Guru Dalam Proses Belajar Mengajar Di Kelas Dan Fasilitas Guru Terhadap Motivasi Belajar Siswa,” Din. Pendidik., vol. 3, no. 1, pp. 79–92, 2008, doi: 10.15294/dp.v3i1.434.
Abdullah Ali, “Peran Guru Dalam Pengelolaan Kelas,” J. Eksp. Media Ilm. Pendidik. Guru Madrasah Ibtidaiyah, vol. 10, no. 2, pp. 20–27, 2022, doi: 10.58645/eksperimental.v10i2.219.
S. Arafa, M. Mursalim, and I. Ihsan, “Pengaruh Kecerdasan Emosional Terhadap Prestasi Belajar Siswa SD Negeri 26 Kota Sorong,” J. Papeda J. Publ. Pendidik. Dasar, vol. 4, no. 1, pp. 47–54, 2022, doi: 10.36232/jurnalpendidikandasar.v4i1.2061.
M. D. Cookson and P. M. R. Stirk, “Penelitian R & D,” pp. 36–49, 2019.
M. Shovian, H. Al, A. P. Kharisma, and N. Santoso, “Pengembangan Aplikasi Sistem Informasi Manajemen Gudang Berbasis Web Menggunakan Metodologi Agile ( Studi Kasus : CV . Jaya Laksa Lestari ),” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 1, pp. 1–10, 2020.
S. Rabiah, “Penggunaan Metode Research and Development dalam Penelitian Bahasa Indonesia di Perguruan Tinggi,” no. April 2015, pp. 1–7, 2018, doi: 10.31227/osf.io/bzfsj.
N. A. S. Badrulhisham and ..., “Emotion recognition using convolutional neural network (CNN),” J. Phys. …, 2021, doi: 10.1088/1742-6596/1962/1/012040.
S. Nita, S. Bitam, M. Heidet, and A. Mellouk, “A new data augmentation convolutional neural network for human emotion recognition based on ECG signals,” Biomed. Signal Process. …, 2022, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809422001021
N. Chouhan, A. Khan, J. Z. Shah, M. Hussnain, and ..., “Deep convolutional neural network and emotional learning based breast cancer detection using digital mammography,” Comput. Biol. …, 2021, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0010482521001128
R. Yanti and F. R. Chan, Pemrograman Dasar Phyton Web Menggunakan Framework Django Untuk Pemula. Kalten: Penerbit Lakeisha, 2023.
F. R. Chan, R. Yanti, and F. Annas, “Development of Interactive Artificial Intelligence-Based Learning Media Using Natural Language Processing Methods In the Subject of Informatics,” BiCED Proceeding, 2023, [Online]. Available: https://proceedings.uinbukittinggi.ac.id/biced/article/view/325
F. R. Chan and E. Maiyana, “Perancangan Aplikasi Pengelolaan Toko Berbasis Web,” J. Teknol. Dan Sist. Inf., vol. 4, no. 1, pp. 75–80, 2023, [Online]. Available: http://jim.teknokrat.ac.id/index.php/sisteminformasi/index
F. R. Chan, D. Harni, M. Ramadhani, Hanifah, and L. Efriyanti, “Perancangan Aplikasi Pengelolaan Gudang Berbasis Android Menggunakan Android Studio,” vol. 3, no. 2, p. 103, 2022, doi: 10.24843/ejmunud.2019.v08.i12.p16.
M. Mukhopadhyay, A. Dey, R. N. Shaw, and ..., “Facial emotion recognition based on textural pattern and convolutional neural network,” 2021 IEEE 4th …, 2021, [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9573860/
S. E. Moon, C. J. Chen, C. J. Hsieh, J. L. Wang, and J. S. Lee, “Emotional EEG classification using connectivity features and convolutional neural networks,” Neural Networks, 2020, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0893608020302987
A. Dehghan, E. G. Ortiz, G. Shu, and S. Z. Masood, “Dager: Deep age, gender and emotion recognition using convolutional neural network,” arXiv Prepr. arXiv1702.04280, 2017, [Online]. Available: https://arxiv.org/abs/1702.04280
A. Amjad, L. Khan, and H. T. Chang, “Effect on speech emotion classification of a feature selection approach using a convolutional neural network,” PeerJ Computer Science. peerj.com, 2021. [Online]. Available: https://peerj.com/articles/cs-766/
D. Issa, M. F. Demirci, and A. Yazici, “Speech emotion recognition with deep convolutional neural networks,” Biomed. Signal Process. Control, 2020, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809420300501
F. González-Hernández and ..., “Recognition of learning-centered emotions using a convolutional neural network,” J. Intell. …, 2018, [Online]. Available: https://content.iospress.com/articles/journal-of-intelligent-and-fuzzy-systems/ifs169514
P. Kaviya and T. Arumugaprakash, “Group facial emotion analysis system using convolutional neural network,” 2020 4th Int. …, 2020, [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9143037/
Downloads
Submitted
Accepted
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Fajri Rinaldi Chan, Firdaus Annas, Yulifda Elin Yuspita, Gusnita Darmawati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.