Implementasi Convolutional Neural Network Berbasis Word Embedding untuk Klasifikasi Pertanyaan Chatbot
Abstract
Chatbot merupakan sistem percakapan berbasis kecerdasan buatan yang mampu memberikan respons otomatis terhadap pertanyaan pengguna secara real-time. Penelitian ini mengimplementasikan metode Convolutional Neural Network (CNN) yang diintegrasikan dengan Word Embedding berbasis Word2Vec untuk mengklasifikasikan pertanyaan pada chatbot Nova AI yang dikembangkan khusus bagi mahasiswa Fakultas Ilmu Komputer dan Teknologi Informasi (FIKTI) Universitas Muhammadiyah Sumatera Utara (UMSU). Dataset terdiri dari 619 pertanyaan dalam bahasa Indonesia yang dikategorikan ke dalam enam kelas intent: dekan, dosen, fakultas, kaprodi, sapaan, dan UKT, dengan pembagian 495 data latih (79,97%) dan 124 data uji (20,03%). Pipeline praproses teks mencakup case folding, tokenisasi, representasi Word2Vec berdimensi 100, pengindeksan kata, dan padding dengan max_len=10. Arsitektur CNN yang dibangun terdiri atas lapisan Embedding, Conv1D (64 filter, kernel 3, ReLU), GlobalMaxPooling1D, Dense 64 unit ReLU, dan Dense output 6 unit Softmax. Model dilatih selama 20 epoch menggunakan optimizer Adam dengan learning rate 0,001 dan fungsi loss Sparse Categorical Crossentropy. Hasil evaluasi menunjukkan akurasi model sebesar 99,19%, dengan satu kesalahan klasifikasi pada intent kaprodi yang teridentifikasi sebagai dekan. Pengujian sistem Nova AI berbasis Streamlit menghasilkan tingkat keberhasilan 83,33% (25 dari 30 skenario pengujian). Penelitian ini membuktikan bahwa kombinasi CNN dan Word Embedding mampu mengklasifikasikan intent chatbot dengan akurasi tinggi dan dapat diimplementasikan dalam aplikasi nyata berbasis web.
References
Adamopoulou, E., & Moussiades, L. (2020). Chatbots: History, technology, and applications. Machine Learning with Applications, 2, 100006. https://doi.org/10.1016/j.mlwa.2020.100006
Chaves, A. P., & Gerosa, M. A. (2021). How should my chatbot interact? A survey on social characteristics in human–chatbot interaction design. International Journal of Human–Computer Interaction, 37(8), 729–758. https://doi.org/10.1080/10447318.2020.1841438
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186. https://doi.org/10.18653/v1/N19-1423
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Hadikosyah, A. A., & Hasibuan, W. R. (2026). Analisis sentimen publik terhadap kenaikan UKT pada Platform X menggunakan Support Vector Machine. Indonesian Journal of Multidisciplinary Scientific Studies, 4(6), 380–388. https://doi.org/10.33151/ijomss.v4i6.1124
Huang, M., Zhu, X., & Gao, J. (2020). Challenges in building intelligent open-domain dialog systems. ACM Transactions on Information Systems, 38(3), 1–32. https://doi.org/10.1145/3383123
Jurafsky, D., & Martin, J. H. (2020). Speech and language processing (3rd ed. draft). Stanford University. https://web.stanford.edu/~jurafsky/slp3/
Kim, Y. (2014). Convolutional neural networks for sentence classification. Proceedings of EMNLP 2014, 1746–1751. https://doi.org/10.3115/v1/D14-1181
Kowsari, K., Meimandi, K. J., Heidarysafa, M., Mendu, S., Barnes, L., & Brown, D. (2019). Text classification algorithms: A survey. Information, 10(4), 150. https://doi.org/10.3390/info10040150
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. http://arxiv.org/abs/1301.3781
Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., & Gao, J. (2022). Deep learning–based text classification: A comprehensive review. ACM Computing Surveys, 54(3), 1–40. https://doi.org/10.1145/3439726
Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37–63.
Smutny, P., & Schreiberova, P. (2020). Chatbots for learning: A review of educational chatbots for the Facebook Messenger. Computers & Education, 151, 103862. https://doi.org/10.1016/j.compedu.2020.103862
Tan, L., Yi, J., & Yang, F. (2024). Improving performance of massive text real-time classification for document confidentiality management. Applied Sciences, 14(4), 1565. https://doi.org/10.3390/app14041565
Wang, H., & Li, X. (2022). Chinese news text classification based on convolutional neural network. Journal on Big Data, 4(1), 41–60. https://doi.org/10.32604/jbd.2022.027717
Wang, H., Tian, K., Wu, Z., & Wang, L. (2020). A short text classification method based on convolutional neural network and semantic extension. International Journal of Computational Intelligence Systems, 14(1), 367. https://doi.org/10.2991/ijcis.d.201207.001
Yan, D., Li, K., Gu, S., & Yang, L. (2020). Network-based bag-of-words model for text classification. IEEE Access, 8, 82641–82652. https://doi.org/10.1109/ACCESS.2020.2991074
Yogatama, D., Dyer, C., Ling, W., & Blunsom, P. (2017). Generative and discriminative text classification with recurrent neural networks. arXiv preprint arXiv:1703.01898. http://arxiv.org/abs/1703.01898
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018). Recent trends in deep learning based natural language processing. IEEE Computational Intelligence Magazine, 13(3), 55–75. https://doi.org/10.1109/MCI.2018.2840738
Zhang, X., & LeCun, Y. (2016). Text understanding from scratch. Advances in Neural Information Processing Systems. http://arxiv.org/abs/1502.01710
Copyright (c) 2026 Rayhan Pratama, Irvan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
