Deteksi Depresi Pengguna Twitter Indonesia Menggunakan LSTM-RNN
DOI:
https://doi.org/10.23887/janapati.v11i3.50674Keywords:
NLP, Klasifikasi Teks, LSTM-RNN, Deteksi DepresiAbstract
Perkembangan media sosial yang semakin pesat, menciptakan keberagaman microblogging sosial, mendorong orang untuk mengekspresikan perasaan dan pendapat, Setiap tweet pada twitter mewakili ekspresi emosional penggunanya, hal ini dapat dijadikan studi kasus dalam mendeteksi kasus depresi dan menilai emosional pengguna twitter. Deteksi dan pencegahan depresi sangat sulit untuk dideteksi dan telah menjadi topik penelitian yang sangat menarik untuk diteliti sejak dekade terakhir. Beberapa penelitian yang berkaitan dengan twitter untuk mendeteksi pengguna media sosial yang mengalami depresi. Salah satu penelitian deteksi depresi melalui twitter menyimpulkan bahwa adanya korelasi antara keadaan depresi pengguna twitter terhadap sentiment yang mereka tweet menggambarkan keadaan depresi pengguna tersebut. Tujuan penelitian ini penelitian kami adalah untuk mengembangkan dan mengoptimalkan penelitian sebelumnya menggunakan metode yang berbeda yakni LSTM-RNN, dan mendeteksi depresi pada tweet twitter indonesia. Dataset yang digunakan berjumlah 5.494 baris tweet, dimana data kelas normal berjumlah 2.747 baris tweet dan data depresi berjumlah 2.747 baris tweet setelah dilakukan balancing data, dataset sebelum digunakan data dilakukan proses preprocessing terlebih dahulu sebelum masuk ke proses pelatihan. Hasil dari penelitian dengan menggunakan metode LSTM-RNN memperoleh nilai presisi, recall, dan F1-score diperoleh masing-masing 86%, 86%, dan 86%, sedangkan akurasinya adalah 86%. Sistem deteksi ujaran depresi diharapkan dapat membantu menganalisa depresi masyarakat di media sosial.
References
M. Abdullah and S. Shaikh, “TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning,” NAACL HLT 2018 - Int. Work. Semant. Eval. SemEval 2018 - Proc. 12th Work., pp. 350–357, 2018, doi: 10.18653/v1/s18-1053.
Simon Kemp, “Digital 2022: Indonesia-DataReportal,” Global Digital Insights, 2022.
A. M. Kaplan and M. Haenlein, “Users of the world, unite! The challenges and opportunities of Social Media,” Bus. Horiz., vol. 53, no. 1, 2010, doi: 10.1016/j.bushor.2009.09.003.
S. Stieglitz, M. Mirbabaie, B. Ross, and C. Neuberger, “Social media analytics – Challenges in topic discovery, data collection, and data preparation,” Int. J. Inf. Manage., vol. 39, no. December 2017, pp. 156–168, 2018, doi: 10.1016/j.ijinfomgt.2017.12.002.
K. Pranav, “Neural Network Based System to Detect Depression in Twitter Users via Sentiment Analysis,” Int. Res. J. Eng. Technol., pp. 1449–1451, 2018, [Online]. Available: www.irjet.net
M. K. Neighbor, A. P. Tirtopangarsa, W. Maharani, T. Informasi, and U. Telkom, “Sentiment Analysis of Depression Detection on Twitter Social Media Users Using the K-Nearest Neighbor Method,” J. SEMNASIF, pp. 247–258, 2021.
B. Y. Ziwei and H. N. Chua, “An application for classifying depression in tweets,” 2019. doi: 10.1145/3366650.3366653.
A. Chatterjee, U. Gupta, M. K. Chinnakotla, R. Srikanth, M. Galley, and P. Agrawal, “Understanding Emotions in Text Using Deep Learning and Big Data,” Comput. Human Behav., vol. 93, 2019, doi: 10.1016/j.chb.2018.12.029.
M. Abadi et al., “Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv 2016,” arXiv preprint arXiv:1603.04467. 2019.
M. S. Saputri, R. Mahendra, and M. Adriani, “Emotion Classification on Indonesian Twitter Dataset,” 2019. doi: 10.1109/IALP.2018.8629262.
A. D. L, B. Harijanto, and F. Rahutomo, “Implementasi Deep Learning Untuk Deteksi Ekspresi Emosi Pada Twitter,” pp. 3–6, 2020.
N. Hilmiaji, K. M. Lhaksmana, and M. D. Purbolaksono, “Identifying Emotion on Indonesian Tweets using Convolutional Neural Networks,” no. 10, pp. 584–593, 2021.
T. I. Sari, Z. N. Ardilla, N. Hayatin, and R. Maskat, “Abusive comment identification on Indonesian social media data using hybrid deep learning,” IAES Int. J. Artif. Intell., vol. 11, no. 3, pp. 895–904, 2022, doi: 10.11591/ijai.v11.i3.pp895-904.
A. Dirgayunita, “Depresi: Ciri, Penyebab dan Penangannya,” J. An-Nafs Kaji. Penelit. Psikol., vol. 1, no. 1, 2016, doi: 10.33367/psi.v1i1.235.
F. Chollet and & O., “Keras: the Python deep learning API,” Keras: the Python deep learning API, 2020.
Y. Li and T. Yang, “Word Embedding for Understanding Natural Language: A Survey,” 2018. doi: 10.1007/978-3-319-53817-4_4.
H. Sak, A. Senior, and F. Beaufays, “Long short-term memory recurrent neural network architectures for large scale acoustic modeling,” 2014. doi: 10.21437/interspeech.2014-80.
M. Rizki, S. Basuki, and Y. Azhar, “Implementasi Deep Learning Menggunakan Arsitektur Long Short Term Memory(LSTM) Untuk Prediksi Curah Hujan Kota Malang,” J. Repos., vol. 2, no. 3, 2020, doi: 10.22219/repositor.v2i3.470.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, 2014.
N. Rochmawati, H. B. Hidayati, Y. Yamasari, H. P. A. Tjahyaningtijas, W. Yustanti, and A. Prihanto, “Analisa Learning Rate dan Batch Size pada Klasifikasi Covid Menggunakan Deep Learning dengan Optimizer Adam,” J. Inf. Eng. Educ. Technol., vol. 5, no. 2, 2021, doi: 10.26740/jieet.v5n2.p44-48.
“Keras: Introduction to the Adam Optimization Algorithm,” OnnoCenterWiki. https://lms.onnocenter.or.id/wiki/index.php/Keras:_Introduction_to%0A_the_Adam_Optimization_Algorithm (accessed Nov. 09, 2021)
M. Hossin, M. N. Sulaiman, A. Mustapha, N. Mustapha, and R. W. Rahmat, “A hybrid evaluation metric for optimizing classifier,” 2011. doi: 10.1109/DMO.2011.5976522.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Ivan Dwi Nugraha, Yufis Azhar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Janapati agree to the following terms:- Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work. (See The Effect of Open Access)
