Compound Emotional Extraction of Indonesian Sentences Using Convolutional Neural Network
Abstract
Facial expressions can strengthen the information conveyed in interactive communication. In the field of developing virtual characters specifically for facial characters, facial expressions are needed to animate a facial virtual character to make it look natural like a human. One type of emotional expression is a compound emotional expression, which is a combination of two or more basic emotions. For example, the expression of disappointed emotions is a combination of anger and sadness. Facial expressions can appear due to emotional stimulation, one of which is the meaning of the sentence. This research aims to extract emotional data from Indonesian sentences using the multi-label classification process of the CNN model so as to produce compound facial expressions that are applied in virtual character animation. The basic emotion classes used in the classification process are anger, disgust, fear, happiness, sadness, and surprise. Based on the experimental results, the CNN model can produce an accuracy of 94.5% with the composition of training data and test data is 8: 2. The classification process result shows that each sentence can produce more than one basic emotion class that forms compound expressions. The results of the visualization of compound expressions for each sentence can represent compound expressions.
References
T.I. Kusumawati, “Komunikasi Verbal dan Nonverbal,” Jurnal Pendidik. dan Konseling, Vol. 6, No. 2, hal. 83–98, 2016.
P. Ekman dan D. Cordaro, “What is Meant by Calling Emotions Basic,” Emot. Rev., Vol. 3, No. 4, hal. 364–370, Okt. 2011.
J.E. Prawitasari, “Mengenal Emosi Melalui Komunikasi Nonverbal,” Bul. Psikol., Vol. 3, No. 1, hal. 27–43, 2016.
B. Denafri, “Struktur Informasi Kalimat Bahasa Indonesia,” J. Ilmiah Kebahasaan dan Kesastraan, Vol. 6, No. 1, hal. 43-49, Jun. 2018.
S.S.T.W. Sasangka, Seri Penyuluhan Bahasa Indonesia: Kalimat, Jakarta, Indonesia: Pusat Pembinaan dan Pemasyarakatan; Badan Pengembangan dan Pembinaan Bahasa; Kementrian Pendidikan dan Kebudayaan, 2015.
Y. Kim, “Convolutional Neural Networks for Sentence Classification,” Proc. the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, hal. 1746–1751.
W. Agastya dan Aripin, “Pemetaan Emosi Dominan pada Kalimat Majemuk Bahasa Indonesia Menggunakan Multinomial Naïve Bayes,” J.
Nas. Teknik Elektro dan Teknologi Informasi (JNTETI), Vol. 9, No. 2, hal. 171–179, 2020.
N.A. Shafira dan Irhamah, “Klasifikasi Sentimen Ulasan Film Indonesia dengan Konversi Speech-to-Text (STT) Menggunakan Metode Convolution Neural Network (CNN),” Jurnal Sains dan Seni ITS, Vol. 9, No. 1, hal. 95-101, 2020.
I.C. Irsan dan M.L. Khodra, “Hierarchical Multi-Label News Article Classification with Distributed Semantic Model Based Features,” Int. Journal of Advances in Intelligent Informatics, Vol. 5, No. 1, hal. 40-47, 2019.
S. Sirattanajakarin dan P. Thusaranon, “Movie Genre in Multi-Label Classification Using Semantic Extraction from Only Movie Poster,” ICCCM 2019: Proc. the 2019 7th International Conference on Computer and Communications Management, 2019, hal. 23-27.
A. Jain, G. Kulkarni, dan V. Shah, “Natural Language Processing,” Int. Journal of Computer Sciences and Engineering (IJCSE), Vol. 6, No. 1, hal. 161-167, 2018.
N.I. Widiastuti, “Convolution Neural Network for Text Mining and Natural Language Processing,” IOP Conference Series: Materials Science and Engineering, Vol. 662, No. 5, hal. 1-6, 2019.
P. Zhou, Z. Qi, S. Zheng, J. Xu, H. Bao, dan B. Xu, “Text Classification Improved by Integrating Bidirectional LSTM with Two-Dimensional Max Pooling,” Proc. COLING 2016 - 26th International Conference on Computational Linguistics, 2016, hal. 3485–3495.
Satyabrata, S. Chakraborty, dan H.-C. Kim, “Convolution Neural Network-Based Model for Web-Based Text Classification,” Int. Journal of Electrical and Computer Engineering (IJECE), Vol. 9, No. 6, hal. 5185-5191.2019.
G. Onwujekwe dan V. Yoon, “Activation Functions and their Impact on the Training and Performance of Convolution Neural Network Models,” Proc. the Americas Conference on Information Systems (AMCIS), 2020, hal. 1-5.
P. Ekman dan W.V. Friesen, Facial Action Coding System: A Technique for the Measurement of Facial Movement, Palto Alto, USA: Consulting Psychologies Press, 1978.
S. Du, Y. Tao, dan A.M. Martinez, “Compound Facial Expressions of Emotion,” Proc. of the National Academy of Sciences, 2014, hal. 1454-1462.
F. Nie, Z. Hu, dan X. Li, “An Investigation for Loss Functions Widely Used in Machine Learning,” Communication in Information and System, Vol. 18, No. 1, hal. 37-52, 2018.
I. Duntsch dan G. Gediga, "Confusion Matrices and Rough Set Data Analysis," Journal of Physics: Conf. Series, Vol. 1229, hal. 1-6, 2019.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
