Deteksi Aspek Review E-Commerce Menggunakan IndoBERT Embedding dan CNN
DOI:
https://doi.org/10.52985/insyst.v5i1.267Keywords:
Aspect Category Detection, CNN, IndoBERT, ReviewAbstract
Dengan semakin berkembangnya teknologi informasi, maka muncul istilah e-commerce dalam dunia bisnis. Pada e-commerce ada fitur review, pelanggan dapat memberikan review berupa teks, gambar, dan bintang. Review tersebut merupakan opini dari pelanggan terkait barang yang dibeli. Tetapi pada kebanyakan e-commerce tidak ada fitur kategori terkait review hal ini membuat calon pembeli kesusahan dalam menganalisa secara manual. Aspect-based sentiment analysis (ABSA) merupakan solusi dari permasalahan tersebut. ABSA memiliki tiga tugas salah satunya Aspect Category Detection yang memiliki fungsi untuk menggabungkan review pelanggan menjadi beberapa aspek dimana aspek-aspek tersebut sudah didefinisikan terlebih dahulu. Cukup banyak penelitian terkait Aspect Category Detection dengan mengunakan machine learning. Dari beberapa metode yang diuji, Convolutional Neural Network (CNN) merupakan metode terbaik. Selain itu penggunaan BERT sebagai word embedding menghasilkan output yang bagus baik dari pada word embedding konvensional. Penelitian ini menggunakan dataset dari e-commerce Bukalapak dengan 3114 review dan 6 aspek (Akurasi, Pengiriman, Kualitas, Harga, Pengemasan, dan Pelayanan). Berdasarkan ujicoba dengan menggunakan IndoBERT sebagai word embedding dan CNN untuk deteksi aspek, maka didapatkan akurasi sebesar 94,86%. Dengan demikian model tersebut dapat digunakan untuk deteksi aspek. Selain itu, metode CNN mendapatkan hasil yang lebih baik dari pada metode LSTM.
References
D. Hendarsyah, “E-Commerce Di Era Industri 4.0 Dan Society 5.0,” Iqtishaduna, vol. 8, no. 2, pp. 171–184, Dec. 2019, 10.46367/iqtishaduna.v8i2.170.
R. P. Ananda and A. Yuniawan, “Studi Empiris Kepuasan Pelanggan E-Commerce Secara Global,” SLJIL, vol. 6, no. 7, p. 3499, Jul. 2021, 10.36418/syntax-literate.v6i7.3541.
Md. A. Rahman and E. Kumar Dey, “Aspect Extraction from Bangla Reviews using Convolutional Neural Network,” in 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), Kitakyushu, Japan, Jun. 2018, pp. 262–267, 10.1109/ICIEV.2018.8641050.
T. Alvarez-López, J. Juncal-Martínez, M. Fernández-Gavilanes, E. Costa-Montenegro, dan F.J. González-Castã, “SVM and CRF for Aspect Detection and Unsupervised Aspect-Based Sentiment Analysis,” Proc. 10th Int. Work. Semant. Eval., 2016, hal. 306–311.
M. Pontiki, D. Galanis, J. Pavlopoulos, H. Papageorgiou, I. Androutsopoulos, dan S. Manandhar, “SemEval-2014 Task 4: Aspect Based Sentiment Analysis,” Proc. 8th Int. Work. Semant. Eval., 2015, hal. 27–35.
H. Papageorgiou, I. Androutsopoulos, D. Galanis, M. Pontiki, dan S. Manandhar, “SemEval-2015 Task 12: Aspect Based Sentiment Analysis,” Proc. 9th Int. Work. Semant. Eval., 2015, hal. 486–495.
M. Pontiki, D. Galanis, H. Papageorgiou, dkk., “SemEval-2016 Task 5: Aspect Based Sentiment Analysis,” Proc. 10th Int. Work. Semant. Eval., 2016, hal. 19–30.
S. Movahedi, E. Ghadery, H. Faili, dan A. Shakery, “Aspect Category Detection via Topic-Attention Network,” arXiv Prepr. arXiv1901.01183, hal. 1–9, 2019.
H. H. Do, P. Prasad, A. Maag, and A. Alsadoon, “Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review,” Expert Systems with Applications, vol. 118, pp. 272–299, Mar. 2019, 10.1016/j.eswa.2018.10.003.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv:1810.04805 [Cs].
P. R. Amalia and E. Winarko, “Aspect-Based Sentiment Analysis on Indonesian Restaurant Review Using a Combination of Convolutional Neural Network and Contextualized Word Embedding,” Indonesian J. Comput. Cybern. Syst., vol. 15, no. 3, p. 285, Jul. 2021. 10.22146/ijccs.67306.
R. Man and K. Lin, “Sentiment Analysis Algorithm Based on BERT and Convolutional Neural Network,” in 2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), Dalian, China, pp. 769–772, Apr. 2021. 10.1109/IPEC51340.2021.9421110.
W. Quan, Z. Chen, J. Gao, and X. T. Hu, “Comparative Study of CNN and LSTM based Attention Neural Networks for Aspect-Level Opinion Mining,” in 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, Dec. 2018, pp. 2141–2150. 10.1109/BigData.2018.8622150.
S. Poria, E. Cambria, and A. Gelbukh, “Aspect extraction for opinion mining with a deep convolutional neural network,” Knowledge-Based Systems, vol. 108, pp. 42–49, Sep. 2016, 10.1016/j.knosys.2016.06.009.
KIM, Y., Convolutional neural networks for sentence classification. In: EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. hal.1746-1751. 2014.
M. D. Zeiler, “ADADELTA: An Adaptive Learning Rate Method.” arXiv, Dec. 22, 2012.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization.” arXiv, Jan. 29, 2017.
T. Dozat, “INCORPORATING NESTEROV MOMENTUM INTO ADAM,” 2016.
S. Ruder, “An overview of gradient descent optimization algorithms.” arXiv, Jun. 15, 2017.
M. M. Abdelgwad, “Arabic aspect based sentiment classification using BERT.” arXiv, Nov. 27, 2021.
M. O. Ibrohim and I. Budi, "Multi-label Hate Speech and Abusive Language Detection in Indonesian Twitter," in Proceedings of the Third Workshop on Abusive Language Online, Florence, Italy, pp. 46-57, 2019. 10.18653/v1/W19-3506.
B. Wilie et al., "IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding," p. 15. arXiv, Oct. 08, 2020.
M. T. Ari Bangsa, S. Priyanta, dan Y. Suyanto, “Aspect-Based Sentiment Analysis of Online Marketplace Reviews Using Convolutional Neural Network,” Indonesian J. Comput. Cybern. Syst., vol. 14, no. 2, p. 123, Apr. 2020
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 INSYST: Journal of Intelligent System and Computation
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
