IMPLEMENTASI RAG MULTIMODAL UNTUK REKOMENDASI TEKS DAN GAMBAR DI E-COMMERCE
Abstract
Penelitian ini mengevaluasi efektivitas Retrieval-Augmented Generation (RAG) Multimodal sebagai sistem rekomendasi di platform e-commerce. Sistem pencarian tradisional, baik berbasis kata kunci maupun semantik, seringkali gagal menangkap niat, konteks, dan aspek visual dari kebutuhan pengguna, yang berdampak negatif pada kualitas pengalaman belanja daring. Meskipun RAG Multimodal menjanjikan interaksi yang lebih holistik, studi empiris mengenai persepsi pengguna terhadap keunggulannya masih terbatas. Penelitian ini bertujuan merancang dan mengimplementasikan sistem RAG Multimodal fungsional, serta mengevaluasi pengalaman pengguna secara kualitatif dibandingkan dengan metode pencarian tradisional. Sebuah aplikasi web e-commerce dikembangkan dengan empat fitur pencarian (kata kunci, semantik teks, semantik gambar, dan RAG Multimodal) menggunakan model SigLIP untuk embedding dan Gemini 2.5 Pro untuk generasi respons. Evaluasi kualitatif dengan desain task scenario dan Think-Aloud Protocol menunjukkan bahwa fitur RAG Multimodal secara konsisten menjadi pilihan utama partisipan, terutama dalam skenario pencarian yang kompleks dan ambigu. Partisipan menilai sistem ini mampu memberikan rekomendasi yang terjustifikasi, adaptif, dan konsultatif, sehingga mengatasi keterbatasan pendekatan konvensional.
Downloads
References
Bach, T. A., Khan, A., Hallock, H., Beltrão, G., & Sousa, S. (2024). A Systematic Literature Review of User Trust in AI-Enabled Systems: An HCI Perspective. International Journal of Human-Computer Interaction, 40(5), 1251–1266. https://doi.org/10.1080/10447318.2022.2138826
Bai, J., Chen, M., Xiaosheng, J. L., Daniel, M., Xu, Y., Akolakis, C., Allen, T., Atkin, D., Bandiera, O., Banerjee, A., Bergquist, L., Chor, D., Donaldson, D., Duflo, E., Faber, B., Hanson, G., Hsieh, C.-T., Jia, P., Khan-Delwal, A., … Xu, D. Y. (2020). Search and Information Frictions on Global E-Commerce Platforms: Evidence from AliExpress. https://doi.org/10.3386/W28100
Erlina F. Santika. (2024). Tingkat Penetrasi Internet Indonesia Capai 79,5% per 2024. https://databoks.katadata.co.id/teknologi-telekomunikasi/statistik/e6f9d69e252de32/tingkat-penetrasi-internet-indonesia-capai-795-per-2024
Ganis Sanhaji, K., & Irsyaad Hizbullah, A. (2024). ) 2024 | 234 Edusaintek: Jurnal Pendidikan. Sains Dan Teknologi, 11(1), 2024–2234. https://doi.org/10.47668/edusaintek.v11i1.999
Google, T. and B. & C. (2025). e-Conomy SEA 2020. https://www.temasek.com.sg/content/dam/temasek-corporate/news-and-views/resources/reports/e-conomy-sea-2020-report.pdf
Gupta, S., Ranjan, R., & Singh, S. N. (2024). A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape, and Future Directions. https://arxiv.org/pdf/2410.12837
Jannach, D. (2021). A Survey on Conversational Recommender Systems. ACM Comput. Surv, 54.
Jovanović, M., Voss, P., Ai, A., & Tx, A. (2024). Towards Incremental Learning in Large Language Models: A Critical Review. https://arxiv.org/pdf/2404.18311
Li, Z., Wang, B., Prince, O., Le Texier, T., & Addai-Dansoh, S. (2025). EXPLORING PERCEPTION OF PLATFORM LANGUAGE ON CONSUMER DECISION MAKING: A COGNITIVE LOAD PERSPECTIVE *.
Liang, W., Zhang, Y., Kwon, Y., Yeung, S., & Zou, J. (2022). Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning. Advances in Neural Information Processing Systems, 35. https://arxiv.org/pdf/2203.02053
Mortaheb, M., Amir, M. A., Khojastepour, ), Chakradhar, S. T., & Ulukus, S. (2025). RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance. https://arxiv.org/pdf/2501.03995
Pratiwi, K. D. (2022). E-COMMERCE AND ECONOMIC GROWTH IN INDONESIA: ANALYSIS OF PANEL DATA REGRESSION. GEMA PUBLICA, 7(1), 171–186. https://doi.org/10.14710/GP.7.1.2022.171-186
Rokon, O. F., Simion, A., Du, W., Wen, M., Yao, H., & Lee, K.-C. (2024). Enhancement of E-commerce Sponsored Search Relevancy with LLM.
Tizar, M., & Azizah, N. (2023). RANCANG BANGUN SISTEM INFORMASI PENJUALAN BERBASIS WEB ( E-COMMERCE) PADA TOKO RUMAH POPOK KINAN. EDUSAINTEK: Jurnal Pendidikan, Sains Dan Teknologi, 10(1), 154–170. https://doi.org/10.47668/EDUSAINTEK.V10I1.664
Copyright (c) 2025 Bagas Wahyu Herdiansyah, Mukhammad Andri Setiawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Jurnal allows anyone to compose, correct, and do derivative works, even for commercial purposes, as long as they credit for the original work. This license is the freest. It is recommended for maximum distribution and use of licensed material.
The submitted paper is assumed not to contain any proprietary materials that are not protected by patent rights or patent applications; The responsibility for technical content and protection of proprietary materials rests with the authors and their organizations and not the responsibility of journal or its editorial staff. The primary (first/appropriate) author is responsible for ensuring that the article has been viewed and approved by all other authors. The author's responsibility is to obtain all necessary copyright waivers to use any copyrighted material in the manuscript before submission.
Jurnal Pendidikan, Sains dan Teknologi allows the author(s) to hold the copyright without restrictions and allow the author(s) to retain publishing rights without restrictions. Jurnal Pendidikan, Sains dan Teknologi CC-BY-SA or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work. Jurnal Pendidikan, Sains dan Teknologi allows the author(s) to hold the copyright without restrictions and allow the author(s) to retain publishing rights without restrictions. Jurnal Pendidikan, Sains dan Teknologi CC-BY-SA or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities Jurnal Pendidikan, Sains dan Teknologi recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY-SA or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
Jurnal Pendidikan, Sains dan Teknologi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
You are free to:
- Share a copy and redistribute the material in any medium or format
- Adapt a remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
