Prediksi Niat Pembelian Kembali Pelanggan Berbasis Sentimen Ulasan Dengan Data Terbatas Menggunakan INDOBERT

• RISTYANI SLAMET
• 14210224

---

ABSTRAK

ABSTRAK

Nama              : Ristyani slamet

NIM                 : 14210224

Program Studi : Ilmu Komputer

Fakultas          : Teknologi Informasi

Jenjang           : Strata Dua (S2)

Konsentrasi     : Data Mining

Judul            : “Prediksi Niat Pembelian Kembali Pelanggan Berbasis Sentimen Ulasan Dengan Data Terbatas Menggunakan IndoBERT”

Niat pembelian kembali merupakan salah satu hal penting bagi perusahaan karena berkaitan dengan loyalitas pelanggan. Dalam industri e-commerce ulasan online dapat menjadi sumber data yang dapat digunakan untuk memprediksi niat pembelian kembali pelanggan. Dalam penelitian ini diusulkan untuk melakukan prediksi terhadap niat pembelian kembali berbasis sentimen analisis dengan menggunakan ulasan online pelanggan terhadap produk yang dibeli dalam Bahasa Indonesia di situs e-commerce Sociolla.com. Pengujian awal dilakukan dengan membandingkan metode machine learning antara lain metode logistic regression, light gradient boosting classifier (LGBM), random forest, support vector classifier (SVC), decision tree classifier, tetapi hasil yang diperoleh mendapatkan hasil akurasi yang rendah, hal ini terjadi karena adanya data yang tidak seimbang, maka dari itu dilakukan teknik oversampling, tetapi hasil yang diperoleh tidak menunjukan perubahan yang signifikan. Dengan demikian, maka dilakukan fine tuning dengan menggunakan metode IndoBERT untuk menghindari masalah overfitting karena dataset yang digunakan terbatas untuk melatih model secara efektif. Hasil yang diperoleh dengan model IndoBERT mendapatkan hasil akurasi terbaik sebesar 96%, f1-score sebesar 95%, recall 93%, dan precision 96%.

KATA KUNCI

Niat pembelian kembali,machine learning,INDOBERT,Online reviews,Fine tuning

---

DAFTAR PUSTAKA

DAFTAR REFERENSI

[1] P. Rita and R. F. Ramos, “Global Research Trends in Consumer Behavior and Sustainability in E-Commerce: A Bibliometric Analysis of the Knowledge Structure,” Sustainability, vol. 14, no. 15, p. 9455, Aug. 2022, doi: 10.3390/su14159455.

[2] C. Gr?dinaru, ?tefan-A. Catan?, S. G. Toma, and A. Barbu, “An Empirical Research of Students’ Perceptions Regarding M-Commerce Acquisitions during the COVID-19 Pandemic,” Sustainability, vol. 14, no. 16, p. 10026, Aug. 2022, doi: 10.3390/su141610026.

[3] Q. Zhou, Z. Xu, and N. Y. Yen, “User sentiment analysis based on social network information and its application in consumer reconstruction intention,” Comput Human Behav, vol. 100, pp. 177–183, Nov. 2019, doi: 10.1016/j.chb.2018.07.006.

[4] A. Maya Nur Lita Program Studi Manajemen Bisnis Syariah, F. Ekonomi dan Bisnis Islam, and I. Surakarta Zakky Fahma Auliya, “Pengaruh Review Online, Kepercayaan Pada Web, Keamanan Bertransaksi Online, dan Privasi Terhadap Niat Pembelian Ulang Pada Toko Online Lazada,” 2019. [Online]. Available: www.internetworldstats.com,

[5] E. Permatasari, H. Luthfiana, N. A. Pratama, and H. Ali, “FAKTOR-FAKTOR YANG MEMPENGARUHI PEMBELIAN ULANG: PROMOSI, HARGA DAN PRODUK (LITERATURE REVIEW PERILAKU KONSUMEN),” vol. 3, no. 5, 2022, doi: 10.31933/jimt.v3i5.

[6] D. Suryadi, “Predicting Repurchase Intention Using Textual Features of Online Customer Reviews,” in 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020, Institute of Electrical and Electronics Engineers Inc., Oct. 2020. doi: 10.1109/ICDABI51230.2020.9325646.

[7] S. Mishra, S. Choubey, A. Choubey, N. Yogeesh, J. Durga Prasad Rao, and P. William, “Data Extraction Approach using Natural Language Processing for Sentiment Analysis,” in 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS), 2022, pp. 970–972. doi: 10.1109/ICACRS55517.2022.10029216.

[8] R. Haque, M. Hasanuzzaman, and A. Way, “Mining purchase intent in twitter,” Computacion y Sistemas, vol. 23, no. 3, pp. 871–881, 2019, doi: 10.13053/CyS-23- 3-3254.

[9] M. Bilal and A. A. Almazroi, “Effectiveness of Fine-tuned BERT Model in Classification of Helpful and Unhelpful Online Customer Reviews,” Electronic Commerce Research, pp. 1–21, 2022, doi: 10.1007/s10660-022-09560-w.

[10] M. A. Rahman and E. Kumar Dey, Aspect Extraction from Bangla Reviews using Convolutional Neural Network. 2018. [Online]. Available: https://github.com/AtikRahman/Bangla

[11] T. Thongtan and T. Phienthrakul, “Sentiment Classification using Document Embeddings trained with Cosine Similarity,” 2019. [Online]. Available: https://aclanthology.org/P19-2057

[12] A. Ezen-Can, “A Comparison of LSTM and BERT for Small Corpus,” Sep. 2020, [Online]. Available: http://arxiv.org/abs/2009.05451

[13] N. Rai, D. Kumar, N. Kaushik, C. Raj, and A. Ali, “Fake News Classification using transformer based enhanced LSTM and BERT,” International Journal of Cognitive Computing in Engineering, vol. 3, pp. 98–105, Jun. 2022, doi: 10.1016/j.ijcce.2022.03.003.

[14] R. Qasim, W. H. Bangyal, M. A. Alqarni, and A. Ali Almazroi, “A Fine-Tuned BERT-Based Transfer Learning Approach for Text Classification,” J Healthc Eng, vol. 2022, 2022, doi: 10.1155/2022/3498123. 39 Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri

[15] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Oct. 2018, [Online]. Available: http://arxiv.org/abs/1810.04805

[16] B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” Sep. 2020, [Online]. Available: http://arxiv.org/abs/2009.05387

[17] I. Suyuti and D. R. Sari S, “Fine-Grained Sentiment Analysis on PeduliLindungi Application Users with Multinomial Naive Bayes-SMOTE,” in 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 2022, pp. 374–378. doi: 10.23919/EECSI56542.2022.9946469.

[18] Z. Li, Y. Fan, B. Jiang, T. Lei, and W. Liu, “A survey on sentiment analysis and opinion mining for social multimedia,” Multimed Tools Appl, vol. 78, no. 6, pp. 6939–6967, Mar. 2019, doi: 10.1007/s11042-018-6445-z.

[19] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Oct. 2018, [Online]. Available: http://arxiv.org/abs/1810.04805

[20] P. Ganesh et al., “Compressing Large-Scale Transformer-Based Models: A Case Study on BERT,” Feb. 2020, doi: 10.1162/tacl_a_00413.

[21] M. Khan, M. R. Naeem, E. A. Al-Ammar, W. Ko, H. Vettikalladi, and I. Ahmad, “Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning,” Electronics (Switzerland), vol. 11, no. 2, Jan. 2022, doi: 10.3390/electronics11020206.

[22] J. Devlin, M.-W. Chang, K. Lee, K. T. Google, and A. I. Language, “BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding.” [Online]. Available: https://github.com/tensorflow/tensor2tensor

[23] S. M. Isa, G. Nico, and M. Permana, “INDOBERT FOR INDONESIAN FAKE NEWS DETECTION,” ICIC Express Letters, vol. 16, no. 3, pp. 289–297, Mar. 2022, doi: 10.24507/icicel.16.03.289.

[24] D. Fan, L. Wan, W. Xu, and S. Wang, “A bi-directional attention guided crossmodal network for music based dance generation,” Computers and Electrical Engineering, vol. 103, p. 108310, 2022, doi: https://doi.org/10.1016/j.compeleceng.2022.108310.

[25] M. Arevalillo-Herraez, P. Arnau-Gonzalez, and N. Ramzan, “On Adapting the DIET Architecture and the Rasa Conversational Toolkit for the Sentiment Analysis Task,” IEEE Access, vol. 10, pp. 107477–107487, 2022, doi: 10.1109/ACCESS.2022.3213061.

[26] H. Jayadianti et al., “Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN,” ILKOM Jurnal Ilmiah, vol. 14, no. 3, pp. 348–354, 2022, doi: 10.33096/ilkom.v14i3.1505.348-354.

[27] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” Nov. 2020, [Online]. Available: http://arxiv.org/abs/2011.00677

[28] H. Oh, “A YouTube Spam Comments Detection Scheme Using Cascaded Ensemble Machine Learning Model,” IEEE Access, vol. 9, pp. 144121–144128, 2021, doi: 10.1109/ACCESS.2021.3121508.

[29] X. Lin, “Sentiment Analysis of E-commerce Customer Reviews Based on Natural Language Processing,” in Proceedings of the 2020 2nd International Conference on Big Data and Artificial Intelligence, New York, NY, USA: ACM, Apr. 2020, pp. 32– 36. doi: 10.1145/3436286.3436293.

[30] Md. R. Bhuiyan, M. H. Mahedi, N. Hossain, Z. N. Tumpa, and S. A. Hossain, “An Attention Based Approach for Sentiment Analysis of Food Review Dataset,” in 2020 11th International Conference on Computing, Communication and 40 Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri Networking Technologies (ICCCNT), IEEE, Jul. 2020, pp. 1–6. doi: 10.1109/ICCCNT49239.2020.9225637.

[31] G. M. Shahariar, S. Biswas, F. Omar, F. M. Shah, and S. Binte Hassan, “Spam Review Detection Using Deep Learning,” in 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), IEEE, Oct. 2019, pp. 0027–0033. doi: 10.1109/IEMCON.2019.8936148.

[32] I. Priyadarshini and C. Cotton, “A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis,” J Supercomput, vol. 77, no. 12, pp. 13911– 13932, Dec. 2021, doi: 10.1007/s11227-021-03838-w.

[33] K. Machova, M. Mach, and M. Vasilko, “Comparison of Machine Learning and Sentiment Analysis in Detection of Suspicious Online Reviewers on Different Type of Data,” Sensors, vol. 22, no. 1, p. 155, Dec. 2021, doi: 10.3390/s22010155.

[34] N. Liu, X. Li, E. Qi, M. Xu, L. Li, and B. Gao, “A novel ensemble learning paradigm for medical diagnosis with imbalanced data,” IEEE Access, vol. 8, pp. 171263– 171280, 2020, doi: 10.1109/ACCESS.2020.3014362.

[35] A. Fatima, L. Ying, T. Hills, and M. Stella, “DASentimental: Detecting depression, anxiety and stress in texts via emotional recall, cognitive networks and machine learning,” Oct. 2021.

[36] X. Gao, R. Tan, and G. Li, “Research on Text Mining of Material Science Based on Natural Language Processing,” IOP Conf Ser Mater Sci Eng, vol. 768, no. 7, p. 072094, Mar. 2020, doi: 10.1088/1757-899X/768/7/072094.

[37] Z. Jiang, B. Gao, Y. He, Y. Han, P. Doyle, and Q. Zhu, “Text Classification Using Novel Term Weighting Scheme-Based Improved TF-IDF for Internet Media Reports,” Math Probl Eng, vol. 2021, pp. 1–30, Mar. 2021, doi: 10.1155/2021/6619088.

[38] C.-J. Liu, T.-S. Huang, P.-T. Ho, J.-C. Huang, and C.-T. Hsieh, “Machine learningbased e-commerce platform repurchase customer prediction model,” PLoS One, vol. 15, no. 12, p. e0243105, Dec. 2020, doi: 10.1371/journal.pone.0243105.

[39] H. Oh, “A YouTube Spam Comments Detection Scheme Using Cascaded Ensemble Machine Learning Model,” IEEE Access, 2021, doi: 10.1109/ACCESS.2021.3121508.

[40] H. Tufail, M. U. Ashraf, K. Alsubhi, and H. M. Aljahdali, “The Effect of Fake Reviews on e-Commerce During and After Covid-19 Pandemic: SKL-Based Fake Reviews Detection,” IEEE Access, vol. 10, pp. 25555–25564, 2022, doi: 10.1109/ACCESS.2022.3152806.

[41] A. Sharma and M. O. Shafiq, “A Comprehensive Artificial Intelligence Based User Intention Assessment Model from Online Reviews and Social Media,” Applied Artificial Intelligence, vol. 36, no. 1, 2022, doi: 10.1080/08839514.2021.2014193.

[42] A. Sharma and M. Omair Shafiq, “Predicting purchase probability of retail items using an ensemble learning approach and historical data,” in 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, Dec. 2020, pp. 723–728. doi: 10.1109/ICMLA51294.2020.00118.

[43] R. Haque, M. Hasanuzzaman, A. Ramadurai, and A. Way, “Mining Purchase Intent in Twitter,” Computación y Sistemas, vol. 23, no. 3, Oct. 2019, doi: 10.13053/cys-23-3-3254.

[44] M. E. Basiri, S. Nemati, M. Abdar, E. Cambria, and U. R. Acharya, “ABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysis,” Future Generation Computer Systems, vol. 115, pp. 279–294, Feb. 2021, doi: 10.1016/j.future.2020.08.005.

[45] X. Lin, “Sentiment Analysis of E-commerce Customer Reviews Based on Natural Language Processing,” in Proceedings of the 2020 2nd International Conference on Big Data and Artificial Intelligence, New York, NY, USA: ACM, Apr. 2020, pp. 32– 36. doi: 10.1145/3436286.3436293. 41 Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri

[46] N. Hossain, Md. R. Bhuiyan, Z. N. Tumpa, and S. A. Hossain, “Sentiment Analysis of Restaurant Reviews using Combined CNN-LSTM,” in 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), IEEE, Jul. 2020, pp. 1–5. doi: 10.1109/ICCCNT49239.2020.9225328.

[47] S. Atouati, X. Lu, and M. Sozio, “Negative Purchase Intent Identification in Twitter,” in The Web Conference 2020 - Proceedings of the World Wide Web Conference, WWW 2020, Association for Computing Machinery, Inc, Apr. 2020, pp. 2796–2802. doi: 10.1145/3366423.3380040.

[48] Syaiful Imron, E. I. Setiawan, Joan Santoso, and Mauridhi Hery Purnomo, “Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 3, pp. 586–591, Jun. 2023, doi: 10.29207/resti.v7i3.4751.

[49] R. Mas, R. W. Panca, K. Atmaja1, and W. Yustanti2, “Analisis Sentimen Customer Review Aplikasi Ruang Guru dengan Metode BERT (Bidirectional Encoder Representations from Transformers),” JEISBI, vol. 02, p. 2021.