@article{ART003367449},
author={Jung Yeong Kyu and Kim Seung In},
title={A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis},
journal={Industry Promotion Research},
issn={2466-1139},
year={2026},
volume={11},
number={3},
pages={99-108},
doi={10.21186/IPR.2026.11.3.099}
TY - JOUR
AU - Jung Yeong Kyu
AU - Kim Seung In
TI - A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis
JO - Industry Promotion Research
PY - 2026
VL - 11
IS - 3
PB - Industrial Promotion Institute
SP - 99
EP - 108
SN - 2466-1139
AB - While Generative AI is innovating advertising production, prompt writing still heavily relies on designers' subjective intuition. To address this limitation, this study proposes a data-driven methodology for designing objective prompts by analyzing actual consumer review data. Focusing on online reviews for a skincare product, key experience keywords were extracted via TF-IDF analysis and consumer experience types were classified using K-means clustering. Based on the core clusters, a "Prompt Mapping" structure was developed to translate consumers' unstructured language into specific visual cues. Ultimately, utilizing the Nano Banana Pro AI model, high-quality commercial advertising images optimized for each experience type were successfully generated. This research provides a systematic guideline for producing objective advertising content that accurately reflects real consumer needs.
KW - Generative AI;Consumer Review;Text Mining;K-means Clustering;Prompt Engineering;AI Prompt;Advertising Image
DO - 10.21186/IPR.2026.11.3.099
ER -
Jung Yeong Kyu and Kim Seung In. (2026). A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis. Industry Promotion Research, 11(3), 99-108.
Jung Yeong Kyu and Kim Seung In. 2026, "A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis", Industry Promotion Research, vol.11, no.3 pp.99-108. Available from: doi:10.21186/IPR.2026.11.3.099
Jung Yeong Kyu, Kim Seung In "A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis" Industry Promotion Research 11.3 pp.99-108 (2026) : 99.
Jung Yeong Kyu, Kim Seung In. A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis. 2026; 11(3), 99-108. Available from: doi:10.21186/IPR.2026.11.3.099
Jung Yeong Kyu and Kim Seung In. "A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis" Industry Promotion Research 11, no.3 (2026) : 99-108.doi: 10.21186/IPR.2026.11.3.099
Jung Yeong Kyu; Kim Seung In. A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis. Industry Promotion Research, 11(3), 99-108. doi: 10.21186/IPR.2026.11.3.099
Jung Yeong Kyu; Kim Seung In. A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis. Industry Promotion Research. 2026; 11(3) 99-108. doi: 10.21186/IPR.2026.11.3.099
Jung Yeong Kyu, Kim Seung In. A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis. 2026; 11(3), 99-108. Available from: doi:10.21186/IPR.2026.11.3.099
Jung Yeong Kyu and Kim Seung In. "A Study on A Data-Driven Prompt Design Methodology for Generative AI Advertising Images Based on Consumer Review Data: Focusing on TF-IDF and Cluster Analysis" Industry Promotion Research 11, no.3 (2026) : 99-108.doi: 10.21186/IPR.2026.11.3.099
