Evaluasi Model Distilbert dalam Prediksi Sentimen Ulasan Makanan Amazon

Jofan Vernanda Wicaksono; Ananda Bagus Fatchurroziq; Muhammad Azzakafuadi; M Naufal Anjab Septyan

doi:10.53624/jsitik.v4i2.654

Authors

Jofan Vernanda Wicaksono Universitas Nusantara PGRI Kediri
Ananda Bagus Fatchurroziq Universitas Nusantara PGRI Kediri
Muhammad Azzakafuadi Universitas Nusantara PGRI Kediri
M Naufal Anjab Septyan Universitas Nusantara PGRI Kediri

DOI:

https://doi.org/10.53624/jsitik.v4i2.654

Keywords:

Sentiment Analysis, Amazon, Product Reviews, Machine Learning, DistilBert

Abstract

Latar Belakang: Perkembangan teknologi digital telah menghasilkan ledakan data teks dari berbagai platform daring, terutama dalam bentuk ulasan produk. Tujuan: Tujuan penelitian ini adalah untuk mengevaluasi performa model DistilBERT dalam melakukan klasifikasi sentimen terhadap ulasan makanan dari dataset Amazon Fine Food Reviews. Metode: Dataset yang digunakan terdiri dari 100.000 data ulasan yang telah disederhanakan menjadi dua kelas sentimen: positif dan negatif. Proses pelatihan dilakukan menggunakan pustaka HuggingFace Transformers dengan konfigurasi model DistilBertForSequenceClassification. Hasil: Hasil evaluasi menunjukkan bahwa model DistilBERT mampu mencapai akurasi sebesar 87,44%, membuktikan efektivitasnya dalam menangkap konteks dan makna sentimen dengan efisien. Kesimpulan: Penelitian ini menegaskan bahwa model berbasis transformer ringan seperti DistilBERT dapat menjadi solusi optimal untuk analisis sentimen berskala besar dengan keterbatasan sumber daya komputasi.

Downloads

Download data is not yet available.

References

Ali Saukah dan team. (2017). Pedoman Penulisan Karya Ilmiah. Tugas Akhir, Skripsi, Tesis, Disertasi, Artikel, Makalah, dan Laporan Penelitian. (p. 121).

Cheang, B., Wei, B., Kogan, D., Qiu, H., & Ahmed, M. (2020). Language Representation Models for Fine-Grained Sentiment Classification.

Devlin, J., Chang, M.-W., Lee, K., Google, K. T., & Language, A. I. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Naacl-Hlt 2019, Mlm, 4171–4186. https://aclanthology.org/N19-1423.pdf

Liu, T., Li, S., Dong, Y., Mo, Y., & He, S. (2024). Spam Detection and Classification Based on DistilBERT Deep Learning Algorithm. Applied Science & Engineering Journal for Advanced Research Peer Reviewed and Refereed Journal ISSN, 3, 6–10. https://doi.org/10.5281/zenodo.11180575

McAuley, J., & Leskovec, J. (2013). From amateurs to connoisseurs: Modeling the evolution of user expertise through online reviews. WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web, 897–907. DOI: https://doi.org/10.1145/2488388.2488466

Mutanga, R. T., Naicker, N., & Olugbara, O. O. (2020). Hate speech detection in twitter using transformer methods. International Journal of Advanced Computer Science and Applications, 11(9), 614–620. https://doi.org/10.14569/IJACSA.2020.0110972 DOI: https://doi.org/10.14569/IJACSA.2020.0110972

Nair, A. R., Singh, R. P., Gupta, D., & Kumar, P. (2024). Evaluating the Impact of Text Data Augmentation on Text Classification Tasks using DistilBERT. Procedia Computer Science, 235(2023), 102–111. https://doi.org/10.1016/j.procs.2024.04.013 DOI: https://doi.org/10.1016/j.procs.2024.04.013

Ristyawan, A., Nugroho, A., & Amarya, T. K. (2025). Optimasi Preprocessing Model Random Forest untuk Prediksi Stroke. JATISI (Jurnal Teknik Informatika Dan Sistem Informasi), 12. https://doi.org/10.35957/jatisi.v12i1.9587 DOI: https://doi.org/10.35957/jatisi.v12i1.9587

Rodrawangpai, B., & Daungjaiboon, W. (2022). Improving text classification with transformers and layer normalization. Machine Learning with Applications, 10(March), 100403. https://doi.org/10.1016/j.mlwa.2022.100403 DOI: https://doi.org/10.1016/j.mlwa.2022.100403

Saidani, S., Haddad, R., Bouallegue, R., & Shubair, R. (2022). Fear of falling and risk factors in older adults. Procedia Computer Science, 203, 247–253. https://doi.org/10.1016/j.procs.2022.07.032 DOI: https://doi.org/10.1016/j.procs.2022.07.032

Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. 2–6.

Sari, R. (2019). Analisis Sentimen Review Restoran menggunakan Algoritma Naive Bayes berbasis Particle Swarm Optimization. Jurnal Informatika, 6(1), 23–28. https://doi.org/10.31311/ji.v6i1.4695 DOI: https://doi.org/10.31311/ji.v6i1.4695

Sifa Amalia, B., Umaidah, Y., & Mayasari, R. (2021). Analisis Sentimen Review Pelanggan Restoran Menggunakan Algoritma Support Vector Machine Dan K-Nearest Neighbor. SITEKIN: Jurnal Sains, Teknologi Dan Industri, 19(1), 28–34.

Silva Barbon, R., & Akabane, A. T. (2022). Towards Transfer Learning Techniques—BERT, DistilBERT, BERTimbau, and DistilBERTimbau for Automatic Text Classification from Different Languages: A Case Study. Sensors, 22(21). https://doi.org/10.3390/s22218184 DOI: https://doi.org/10.3390/s22218184

View of Analisis Sentimen Aplikasi Mybca Melalui Review Pengguna Di Google Play Store Menggunakan Algoritma Naive Bayes _ Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi).pdf. (n.d.).