Prediction of Alleged Stress Symptoms based on Indonesian Sentiment Lexicon using Multilayer Perceptron
DOI:
https://doi.org/10.33379/gtech.v7i3.2611Keywords:
Analisis sentimen, gejala stress, Indonesian Sentiment Lexicon, Multilayer Perceptron, TwitterAbstract
Stres adalah fenomena mental atau fisik yang terbentuk melalui penilaian kognitif seseorang terhadap rangsangan dan hasil interaksi seseorang dengan lingkungan. Layaknya penyakit lainnya, stres harus segera ditangani, agar tidak mengganggu keseharian hidup seseorang. Namun, diagnosis mandiri perlu dihindari untuk mencegah terjadinya penanganan yang keliru. Metode terbaru mendeteksi stres melalui media sosial, dimana psikiater dapat mengenali gejala stres seseorang berdasarkan postingan yang terus-menerus di media sosial. Penelitian ini menggunakan dataset dari Twitter, dengan kuesioner DASS-42, model algoritma Multilayer Perceptron dan Indonesian Sentiment Lexicon. Analisis terhadap tweet dapat membentuk model prediktif yang diterapkan untuk mendeteksi sentimen serupa di tweet lain. Percobaan dua kasus uji, yaitu dengan parameter Adam solver menghasilkan akurasi 86%, sedangkan dengan parameter SGD solver menghasilkan akurasi 72%. Hal itu dikarenakan Adam solver bekerja lebih baik dari segi waktu pelatihan dan skor validasi pada kumpulan data yang relatif besar
References
Alamsyah, A., & Indraswari, A. A. (2017, April). Social Network and Sentiment Analysis for Social Customer Relationship Management in Indonesia Banking Sector. pp. 3808-3812.
Aslam, S. (2022). Twitter by the Numbers: Stats, Demographics & Fun Facts. Retrieved from https://www.omnicoreagency.com/: https://www.omnicoreagency.com/twitter-statistics/#:~:text=On average%2C 500 million tweets,200 billion tweets every year
Bhargava, D., & Trivedi, H. (2018). A study of causes of stress and stress management among youth. IRA-International Journal of Management & Social Sciences, 108-117.
De Choudhury, M., Gamon, M., Counts, S., & Horvitz, E. (2021). Predicting depression via social media. Proceedings of the international AAAI conference on web and social media, (pp. 128-137).
Desi, M., Khaira, U., Utomo, P., Utomo, P. E., & Suratno, T. (2021). nalisis Sentimen terhadap Perkuliahan Daring di Indonesia dari Twitter Dataset Menggunakan InSet Lexicon: Sentiment Analysis of Online Lectures in Indonesia from Twitter Dataset Using InSet Lexicon. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 24-33.
Drus, Z., & Khalid, H. (2019). Sentiment analysis in social media and its application: Systematic literature review. Procedia Computer Science, 707-714.
Jalonen, H. (2014). Social media–an arena for venting negative emotions. Online Journal of Communication and Media Technologies, 53-70.
Jones, N. M., Wojcik, S. P., Sweeting, J., & Silver, R. C. (2016). Tweeting negative emotion: An investigation of Twitter data in the aftermath of violence on college campuses. Psychological methods, 526.
Juditha, C. (2017). Hatespeech in Online Media: Jakarta on Election 2017. Jurnal Penelitian Komunikasi Dan Opini Publik, 2, 21.
Lin, H., Jia, J., Qiu, J., Zhang, Y., Shen, G., Xie, L., . . . Chua, T.-S. (2017). Detecting stress based on social interactions in social networks. IEEE Transactions on Knowledge and Data Engineering, 1820-1833.
Livingston, J. S., Selvi, T., & Jenifer, C. S. (2019). A neural network based approach for sentimental analysis on amazon product reviews. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 469-473.
Mara, A. A., Sediyono, E., & Purnomo, H. (2021). K-Nearest Neighbors Algorithm to Student Opinion of the Online Learning Method at Wira Wacana Sumba Christian University. Ultima Infosys: Jurnal Ilmu Sistem Informasi, 87-93.
Mental Health Statistics. (2021). Retrieved from https://www.thezebra.com/: https://www.thezebra.com/resources/research/mental-health-statistics/
Pillai, G., Reshmi, Thelwall, M., & Orasan, C. (2018). Detection of stress and relaxation magnitudes for tweets. Companion Proceedings of the The Web Conference 2018 (pp. 1677-1684). International World Wide Web Conferences Steering Committee.
Putra, J. W. (2019). Pengenalan konsep pembelajaran mesin dan deep learning. Comput. Linguist. Nat. Lang. Process. Lab, 1–235.
Stephen, J. J., & Prabu, P. (2019). Detecting the magnitude of depression in Twitter users using sentiment analysis. International Journal of Electrical and Computer Engineering, 3247.
Tirtopangarsa, A. P., & Maharani, W. (2021). Sentiment Analysis of Depression Detection on Twitter Social Media Users Using the K-Nearest Neighbor Method. Seminar Nasional Informatika (SEMNASIF), (pp. 247-258).
Yuan, X., Wang, L., Yin, X., & Wang, H. (2021). How text sentiment moderates the impact of motivational cues on crowdfunding campaigns. Financial Innovation, 46.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Monika Evelin Johan, Sheyla Aurelia Azka
This work is licensed under a Creative Commons Attribution 4.0 International License.
