Sentimen Ulasan Destinasi Wisata Pulau Bali Menggunakan Bidirectional Long Short Term Memory
Abstract
Pemerintah dan pelaku industri pariwisata mengalami permasalahan dalam menentukan prioritas pengembangan suatu destinasi wisata. Karena itu, diperlukan identifikasi objek wisata yang diminati namun banyak mendapat ulasan buruk melalui ulasan dari masyarakat yang tersebar di internet. Penelitian ini bertujuan melakukan analisis sentimen terhadap ulasan objek wisata di Pulau Bali menggunakan Bi-LSTM dan Word2Vec, sehingga diperoleh model terbaik yang dapat digunakan untuk mengidentifikasi objek wisata potensial namun mendapat ulasan buruk. Bi-LSTM merupakan deep learning yang menawarkan akurasi yang lebih baik daripada LSTM biasa. Sedangkan Word2Vec merupakan pretraining yang dipilih karena dapat menangkap makna semantik teks. Penelitian ini menggunakan data ulasan objek wisata di Pulau Bali yang berasal dari situs tripadvisor.com. Penelitian dimulai dari pengumpulan data, perancangan alur program, preprocessing, pretraining Word2Vec, pembagian data uji dan data latih, pelatihan dan pengujian, serta evaluasi penentuan model terbaik. Akurasi terbaik dihasilkan oleh kombisasi Word2Vec terdiri dari CBOW, Hierarchical Softmax, dimensi 200, Bi-LSTM dengan dropout sebesar 0,5 dan learning rate sebesar 0,0001. Kombinasi tersebut menghasilkan akurasi tertinggi dari keseluruhan 108 kombinasi yaitu sebesar 96,86%, precission sebesar 96,53%, Recall sebesar 96,31%, F1 Measure sebesar 96,41%. Akurasi yang baik tersebut membuktikan bahwa kombinasi parameter Bi-LSTM dan Word2Vec cocok digunakan untuk analisis sentimen ulasan objek wisata di Pulau Bali.
Downloads
References
[2] X. Liu, F. Mehraliyev, C. Liu, and M. Schuckert, “The roles of social media in tourists’ choices of travel components,” Tourist Studies, vol. 20, no. 1, pp. 27–48, 2020, doi: 10.1177/1468797619873107.
[3] Z. Ke, J. Sheng, Z. Li, W. Silamu, and Q. Guo, “Knowledge-Guided Sentiment Analysis Via Learning From Natural Language Explanations,” IEEE Access, vol. 9, pp. 3570–3578, 2021, doi: 10.1109/ACCESS.2020.3048088.
[4] T. Iqbal and S. Qureshi, “The survey: Text generation models in deep learning,” Journal of King Saud University - Computer and Information Sciences, pp. 1–14, Apr. 2020, doi: 10.1016/j.jksuci.2020.04.001.
[5] A. Yenter, “Deep CNN-LSTM with Combined Kernels from Multiple Branches for IMDb Review Sentiment Analysis,” in 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), 2017, pp. 540–546.
[6] H. Ghulam, F. Zeng, W. Li, and Y. Xiao, “Deep Learning-Based Sentiment Analysis for Roman Urdu Text,” Procedia Computer Science, vol. 147, pp. 131–135, 2019, doi: 10.1016/j.procs.2019.01.202.
[7] D. Li and J. Qian, “Text sentiment analysis based on long short-term memory,” in 2016 First IEEE International Conference on Computer Communication and the Internet (ICCCI), Oct. 2016, pp. 471–475, doi: 10.1109/CCI.2016.7778967.
[8] D. I. Af’idah, R. Kusumaningrum, and B. Surarso, “Long Short Term Memory Convolutional Neural Network for Indonesian Sentiment Analysis towards Touristic Destination Reviews,” in 2020 International Seminar on Application for Technology of Information and Communication (iSemantic), Sep. 2020, pp. 630–637, doi: 10.1109/iSemantic50169.2020.9234210.
[9] N. Chen and P. Wang, “Advanced Combined LSTM-CNN Model for Twitter Sentiment Analysis,” in 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), Nov. 2018, pp. 684–687, doi: 10.1109/CCIS.2018.8691381.
[10] Jiddy Abdillah, Ibnu Asror, and Yanuar Firdaus Arie Wibowo, “Emotion Classification of Song Lyrics using Bidirectional LSTM Method with GloVe Word Representation Weighting,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 4, no. 4, pp. 723–729, Aug. 2020, doi: 10.29207/resti.v4i4.2156.
[11] A. Aziz Sharfuddin, M. Nafis Tihami, and M. Saiful Islam, “A Deep Recurrent Neural Network with BiLSTM model for Sentiment Classification,” in 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), Sep. 2018, pp. 1–4, doi: 10.1109/ICBSLP.2018.8554396.
[12] K. Zhang, W. Song, L. Liu, X. Zhao, and C. Du, “Bidirectional Long Short-Term Memory for Sentiment Analysis of Chinese Product Reviews,” in 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC), Jul. 2019, pp. 1–4, doi: 10.1109/ICEIEC.2019.8784560.
[13] W. Li, F. Qi, M. Tang, and Z. Yu, “Bidirectional LSTM with self-attention mechanism and multi-channel features for sentiment classification,” Neurocomputing, vol. 387, pp. 63–77, Apr. 2020, doi: 10.1016/j.neucom.2020.01.006.
[14] G. Xu, Y. Meng, X. Qiu, Z. Yu, and X. Wu, “Sentiment Analysis of Comment Texts Based on BiLSTM,” IEEE Access, vol. 7, pp. 51522–51532, 2019, doi: 10.1109/ACCESS.2019.2909919.
[15] R. P. Nawangsari, R. Kusumaningrum, and A. Wibowo, “Word2Vec for Indonesian Sentiment Analysis towards Hotel Reviews: An Evaluation Study,” Procedia Computer Science, vol. 157, pp. 360–366, 2019, doi: 10.1016/j.procs.2019.08.178.
[16] D. Jatnika, M. A. Bijaksana, and A. A. Suryani, “Word2Vec Model Analysis for Semantic Similarities in English Words,” in Procedia Computer Science, 2019, vol. 157, pp. 160–167, doi: 10.1016/j.procs.2019.08.153.
[17] C. Zhang, X. Wang, S. Yu, and Y. Wang, “Research on Keyword Extraction of Word2vec Model in Chinese Corpus,” in 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), Jun. 2018, pp. 339–343, doi: 10.1109/ICIS.2018.8466534.
[18] I. Guyon, A scaling law for the validation-set training-set size ratio. 1997.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
.png)
