OPTIMIZATION OF HYPERPARAMETERS FOR LSTM-BASED SENTIMENT ANALYSIS ON FACIAL SERUM DATASETS

Merly Saputri; Teguh Iman Hermanto; Imam Ma'ruf Nugroho

doi:10.52436/1.jutif.2024.5.1.1192

Merly Saputri Informatics Engineering, STT Wastukancana Purwakarta, Indonesia
Teguh Iman Hermanto Informatics Engineering, STT Wastukancana Purwakarta, Indonesia
Imam Ma'ruf Nugroho Informatics Engineering, STT Wastukancana Purwakarta, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2024.5.1.1192

Keywords: Activation function, Batch size, Epoch, LSTM, Word2Vec

Abstract

Air pollution and environmental pollutants directly exposed to the skin can damage the skin by accelerating premature aging, increasing the risk of acne, and causing hyperpigmentation. Skincare products such as facial serums containing vitamin C, niacinamide, and vitamin E can effectively address these issues. Awareness of the importance of using facial serums is increasing, so information about product quality through user reviews is essential before placing an order. Sentiment analysis used to classify product reviews into positive or negative, thus providing an overview of the product quality sought before placing an order. This research uses the Long Short-Term Memory (LSTM) method for the sentiment classification process. In this process, the text is converted into a number vector through feature extraction using Word2Vec. In addition, several hyperparameters such as the number of epochs, batch size, and activation function are tested to obtain optimal accuracy results. Testing the number of epochs was conducted with variations of 10, 15, and 20 to determine the performance of the resulting model as the number of epochs increased. Testing the batch size is done to evaluate the batch size in influencing the performance of the model. The batch sizes tested were 16, 32, and 64. In addition, choosing the best activation function can help the LSTM model learn more complex patterns and improve performance in sentiment analysis. The activation functions tested were Softmax, Sigmoid, and Softplus. The results of this study show that the optimal combination of the number of epochs 20, batch size 16, and Softmax activation function can provide optimal accuracy of 96.45%.

Downloads

Download data is not yet available.

References

Widarti, Z. Armah, Herman, and S. Rahayu, “Jurnal Media Analis Kesehatan ISSN : 2621-9557 (Print) ISSN : 2087-1333 (Online),” J. Media Anal. Kesehat., vol. 12, no. 1, pp. 56–65, 2021.

K. Damevska, B. Boev, D. Mirakovski, A. Petrov, R. Darlenski, and V. Simeonovski, “How to prevent skin damage from air pollution. Part 1: Exposure assessment,” Dermatol. Ther., vol. 33, no. 1, 2020, doi: 10.1111/dth.13171.

C. Parrado, S. Mercado-Saenz, A. Perez-Davo, Y. Gilaberte, S. Gonzalez, and A. Juarranz, “Environmental Stressors on Skin Aging. Mechanistic Insights,” Front. Pharmacol., vol. 10, no. July, pp. 1–17, 2019, doi: 10.3389/fphar.2019.00759.

W. Roberts, “Air pollution and skin disorders,” Int. J. Women’s Dermatology, vol. 7, no. 1, pp. 91–97, 2021, doi: 10.1016/j.ijwd.2020.11.001.

H. M. Kim et al., “A Mixture of Topical Forms of Polydeoxyribonucleotide, Vitamin C, and Niacinamide Attenuated Skin Pigmentation and Increased Skin Elasticity by Modulating Nuclear Factor Erythroid 2-like 2,” Molecules, vol. 27, no. 4, pp. 1–20, 2022, doi: 10.3390/molecules27041276.

A. Gueniche et al., “A dermocosmetic formulation containing Vichy volcanic mineralizing water, Vitreoscilla filiformis extract, niacinamide, hyaluronic acid, and vitamin E regenerates and repairs acutely stressed skin,” J. Eur. Acad. Dermatology Venereol., vol. 36, no. S2, pp. 26–34, 2022, doi: 10.1111/jdv.17785.

A. Nuriza and N. H. Indriati, “Klasifikasi Review Produk Kecantikan Pada Aplikasi Sociolla Menggunakan Algoritme Modified K-Nearest Neighbor (MK-NN) dengan Pembobotan BM25,” J. Pengemb. Teknol. Inf. dan …, vol. 4, no. 10, pp. 3426–3431, 2020.

N. Humaira, “ISAS (Attention, Interest, Search, Action, Share) Model of Cosmetics Marketing Communication on Online Beauty Forum (Case-Study: Avoskin Marketing on Sociolla),” MEDIALOG J. Ilmu Komun., vol. 4, no. 1, pp. 186–200, 2021, doi: 10.35326/medialog.v4i1.1031.

C. H. Yutika, A. Adiwijaya, and S. Al Faraby, “Analisis Sentimen Berbasis Aspek pada Review Female Daily Menggunakan TF-IDF dan Naïve Bayes,” J. Media Inform. Budidarma, vol. 5, no. 2, p. 422, 2021, doi: 10.30865/mib.v5i2.2845.

A. Rahman, H. Isnain Sulistiani, B. Miftaq, A. Hurohman Nurkholis, and Styawati, “Analisis Perbandingan Algoritma LSTM dan Naive Bayes untuk Analisis Sentimen,” JEPIN (Jurnal Edukasi dan Penelit. Inform., vol. 8, no. 2, pp. 299–303, 2022, [Online]. Available: https://jurnal.untan.ac.id/index.php/jepin/article/view/54704

M. A. Amrustian, W. Widayat, and A. M. Wirawan, “Analisis Sentimen Evaluasi Terhadap Pengajaran Dosen di Perguruan Tinggi Menggunakan Metode LSTM,” J. Media Inform. Budidarma, vol. 6, no. 1, p. 535, 2022, doi: 10.30865/mib.v6i1.3527.

P. F. Muhammad, R. Kusumaningrum, and A. Wibowo, “Sentiment Analysis Using Word2vec and Long Short-Term Memory (LSTM) for Indonesian Hotel Reviews,” Procedia Comput. Sci., vol. 179, no. 2020, pp. 728–735, 2021, doi: 10.1016/j.procs.2021.01.061.

N. K. Gondhi, Chaahat, E. Sharma, A. H. Alharbi, R. Verma, and M. A. Shah, “Efficient Long Short-Term Memory-Based Sentiment Analysis of E-Commerce Reviews,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/3464524.

F. Z. Ahmad, M. F. S. Arifandy, M. R. Caesarardhi, and N. A. Rakhmawati, “Bagaimana Masyarakat Menyikapi Pembelajaran Tatap Muka: Analisis Komentar Masyarakat pada Media Sosial Youtube Menggunakan Algoritma Deep Learning Sekuensial dan LDA,” J. Linguist. Komputasional, vol. 4, no. 2, p. 40, 2021, doi: 10.26418/jlk.v4i2.57.

W. Hastomo, A. S. Bayangkari Karno, N. Kalbuana, A. Meiriki, and Sutarno, “Characteristic Parameters of Epoch Deep Learning to Predict Covid-19 Data in Indonesia,” J. Phys. Conf. Ser., vol. 1933, no. 1, 2021, doi: 10.1088/1742-6596/1933/1/012050.

M. Fazil, S. Khan, B. M. Albahlal, R. M. Alotaibi, T. Siddiqui, and M. A. Shah, “Attentional Multi-Channel Convolution With Bidirectional LSTM Cell Toward Hate Speech Prediction,” IEEE Access, vol. 11, no. February, pp. 16801–16811, 2023, doi: 10.1109/ACCESS.2023.3246388.

A. Farzad, H. Mashayekhi, and H. Hassanpour, “A comparative performance analysis of different activation functions in LSTM networks for classification,” Neural Comput. Appl., vol. 31, no. 7, pp. 2507–2521, 2019, doi: 10.1007/s00521-017-3210-6.

L. Munkhdalai, T. Munkhdalai, K. H. Park, H. G. Lee, M. Li, and K. H. Ryu, “Mixture of Activation Functions with Extended Min-Max Normalization for Forex Market Prediction,” IEEE Access, vol. 7, pp. 183680–183691, 2019, doi: 10.1109/ACCESS.2019.2959789.

D. Parinata and N. D. Puspaningtyas, “Optimalisasi Penggunaan Google Form terhadap Pembelajaran Matematika,” Mathema J. Pendidik. Mat., vol. 3, no. 1, p. 56, 2021, doi: 10.33365/jm.v3i1.1008.

N. Faridah and B. Sugiantoro, “Analisis Optimasi Pada Algoritma Long ShortTerm Memory Untuk Memprediksi Harga Saham,” J. Media …, vol. 7, pp. 575–582, 2023, doi: 10.30865/mib.v7i1.5421.

W. Hastomo, A. S. B. Karno, N. Kalbuana, E. Nisfiani, and L. ETP, “Optimasi Deep Learning untuk Prediksi Saham di Masa Pandemi Covid-19,” J. Edukasi dan Penelit. Inform., vol. 7, no. 2, p. 133, 2021, doi: 10.26418/jp.v7i2.47411.

W. K. Sari, D. P. Rini, and R. F. Malik, “Text Classification Using Long Short-Term Memory With GloVe Features,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 5, no. 2, p. 85, 2020, doi: 10.26555/jiteki.v5i2.15021.

I. L. Rais and J. Jondri, “Klasifikasi Data Kuesioner dengan Metode Recurrent Neural Network,” eProceedings Eng., vol. 7, no. 1, pp. 2817–2826, 2020.

X. H. Le, H. V. Ho, G. Lee, and S. Jung, “Application of Long Short-Term Memory (LSTM) neural network for flood forecasting,” Water (Switzerland), vol. 11, no. 7, 2019, doi: 10.3390/w11071387.

Y. Romadhoni, K. Fahmi, and H. Holle, “Analisis Sentimen Terhadap PERMENDIKBUD No.30 pada Media Sosial Twitter Menggunakan Metode Naive Bayes dan LSTM,” J. Inform. J. Pengemb. IT, vol. 7, no. 2, pp. 118–124, 2022.

T. Shaik, X. Tao, C. Dann, H. Xie, Y. Li, and L. Galligan, “Sentiment analysis and opinion mining on educational data: A survey,” Nat. Lang. Process. J., vol. 2, no. October 2022, p. 100003, 2023, doi: 10.1016/j.nlp.2022.100003.

A. Ligthart, C. Catal, and B. Tekinerdogan, Systematic reviews in sentiment analysis: a tertiary study, vol. 54, no. 7. Springer Netherlands, 2021. doi: 10.1007/s10462-021-09973-3.

S. Kumawat, I. Yadav, N. Pahal, and D. Goel, “Sentiment analysis using language models: A study,” Proc. Conflu. 2021 11th Int. Conf. Cloud Comput. Data Sci. Eng., pp. 984–988, 2021, doi: 10.1109/Confluence51648.2021.9377043.

H. Hidayah, A. H. Kusumawati, S. Sahevtiyani, and S. Amal, “Literature Review Article: Aktivitas Antioksidan Formulasi Serum Wajah Dari Berbagai Tanaman,” J. Pharmacopolium, vol. 4, no. 2, pp. 75–80, 2021.

A. P. Cahya and N. Fitri, “Formulasi dan uji antioksidan serum wajah berbasis minyak jintan hitam (Nigella Sativa L.) menggunakan metode DPPH,” Asian J. Innov. Entrep., vol. 5, no. 3, pp. 44–53, 2020.

M. A. A. Jihad, Adiwijaya, and W. Astuti, “Analisis sentimen terhadap ulasan film menggunakan algoritma random forest,” e-Proceeding Eng., vol. 8, no. 5, pp. 10153–10165, 2021.

E. Suryati, Styawati, and A. Ari Aldino, “Analisis Sentimen Transportasi Online Menggunakan Ekstraksi Fitur Model Word2vec Text Embedding Dan Algoritma Support Vector Machine (SVM),” J. Teknol. dan Sist. Inf., vol. 4, no. 1, pp. 96–106, 2023.

A. Ridwan, Muhammad; Muzakir, “Model Klasifikasi Ujaran Kebencian pada Data Twitter dengan Menggunakan CNN-LSTM,” Teknomatika, vol. 12, no. 02, pp. 209–218, 2022, [Online]. Available: http://ojs.palcomtech.ac.id/index.php/teknomatika/article/view/604

E. Di. Madyatmadja, B. N. Yahya, and C. Wijaya, “Contextual Text Analytics Framework for Citizen Report Classification: A Case Study Using the Indonesian Language,” IEEE Access, vol. 10, pp. 31432–31444, 2022, doi: 10.1109/ACCESS.2022.3158940.

A. Z. Amrullah, A. Sofyan Anas, and M. A. J. Hidayat, “Analisis Sentimen Movie Review Menggunakan Naive Bayes Classifier Dengan Seleksi Fitur Chi Square,” Jurnal, vol. 2, no. 1, pp. 40–44, 2020, doi: 10.30812/bite.v2i1.804.

M. K. Anam, M. I. Mahendra, W. Agustin, R. Rahmaddeni, and N. Nurjayadi, “Framework for Analyzing Netizen Opinions on BPJS Using Sentiment Analysis and Social Network Analysis (SNA),” INTENSIF J. Ilm. Penelit. dan Penerapan Teknol. Sist. Inf., vol. 6, no. 1, pp. 11–28, 2022, doi: 10.29407/intensif.v6i1.15870.

A. Filcha and M. Hayaty, “Implementasi Algoritma Rabin-Karp untuk Pendeteksi Plagiarisme pada Dokumen Tugas Mahasiswa,” JUITA J. Inform., vol. 7, no. 1, p. 25, 2019, doi: 10.30595/juita.v7i1.4063.

M. U. Albab, Y. Karuniawati P, and M. N. Fawaiq, “Optimization of the Stemming Technique on Text preprocessing President 3 Periods Topic,” J. Transform., vol. 20, no. 2, pp. 1–10, 2023.

D. Alita and A. R. Isnain, “Pendeteksian Sarkasme pada Proses Analisis Sentimen Menggunakan Random Forest Classifier,” J. Komputasi, vol. 8, no. 2, pp. 50–58, 2020, doi: 10.23960/komputasi.v8i2.2615.

M. N. Farid, S. Ferdiana Kusuma, J. Ngagel, and J. Selatan, “Analisis Sentimen pada Media Sosial Twitter Terhadap Kebijakan Pemberlakuan Pembatasan Kegiatan Masyarakat Berbasis Deep Learning,” JEPIN (Jurnal Edukasi dan Penelit. Inform., vol. 8, no. 1, pp. 44–49, 2022, [Online]. Available: https://jurnal.untan.ac.id/index.php/jepin/article/view/49951

T. M. P. Aulia, A. Jamaludin, and ..., “Extractive Text Summerization Pada Berita Berbahasa Indonesia Menggunakan Algoritma Support Vector Machine,” J-SAKTI (Jurnal Sains …, vol. 5, no. September, pp. 727–735, 2021, [Online]. Available: http://ejurnal.tunasbangsa.ac.id/index.php/jsakti/article/view/371

S. Firman, W. Desena, A. Wibowo, M. I. Komputer, and U. B. Luhur, “Penerapan Algoritma Stemming Nazief & Adriani Pada Proses Klasterisasi Berita Berdasarkan Tematik Pada Laman (Web) Direktorat Jenderal HAM Menggunakan Rapidminer,” Syntax J. Inform., vol. 11, no. 02, pp. 10–21, 2022.

L. Hickman, S. Thapa, L. Tay, M. Cao, and P. Srinivasan, “Text Preprocessing for Text Mining in Organizational Research: Review and Recommendations,” Organ. Res. Methods, vol. 25, no. 1, pp. 114–146, 2022, doi: 10.1177/1094428120971683.

A. R. Isnain, A. I. Sakti, D. Alita, and N. S. Marga, “Sentimen Analisis Publik Terhadap Kebijakan Lockdown Pemerintah Jakarta Menggunakan Algoritma Svm,” J. Data Min. dan Sist. Inf., vol. 2, no. 1, p. 31, 2021, doi: 10.33365/jdmsi.v2i1.1021.

A. C. M. V. Srinivas, C. Satyanarayana, C. Divakar, and K. P. Sirisha, “Sentiment Analysis using Neural Network and LSTM,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1074, no. 1, p. 012007, 2021, doi: 10.1088/1757-899x/1074/1/012007.

P. A. Nugroho, I. Fenriana, and R. Arijanto, “Implementasi Deep Learning Menggunakan Convolutional Neural Network ( Cnn ) Pada Ekspresi Manusia,” J. Algor, vol. Vol 2 No.1, pp. 12–21, 2020.

F. Kayim and A. Yilmaz, “Time Series Forecasting With Volatility Activation Function,” IEEE Access, vol. 10, no. October, pp. 104000–104010, 2022, doi: 10.1109/ACCESS.2022.3211312.