An Adaptive AI-Driven Copywriting Framework: Design, Implementation, and Evaluation of a Web-Based GPT-Integrated Content Generation System
DOI:
https://doi.org/10.24246/ijiteb.822026.8-17Keywords:
Artificial Intelligence (AI), Content Generation, GPT API Integration, React–Node JS, AI-Assisted CopywritingAbstract
The increasing demand for scalable and high-quality digital marketing content has exposed limitations in traditional manual copywriting processes, which are time-intensive and difficult to scale. This research proposes an adaptive AI-driven copywriting framework that integrates a full-stack web architecture with optimized prompt engineering strategies for automated content generation. The system is implemented using React.js for the frontend, Node.js with Express for backend services, and a GPT-based API for language generation. Unlike prior implementations, this research introduces a structured prompt optimization mechanism to enhance content relevance and consistency. Experimental evaluation was conducted using multiple datasets of marketing prompts, with comparisons against baseline GPT usage and manual copywriting. Quantitative results show that the proposed system achieves improvements in BLEU (+18.7%) and ROUGE-L (+21.3%) scores over baseline methods. Human evaluation involving 30 participants indicates a significant increase in perceived content quality, coherence, and persuasiveness (p < 0.05). System performance analysis demonstrates an average response time of 1.8–3.0 seconds and a GTmetrix performance score of 82%. The findings confirm that the proposed framework significantly enhances efficiency, scalability, and content quality, contributing to both applied AI systems and intelligent web-based content production.
Downloads
References
A. Madanaguli, V. Parida, D. Sjodin, and P. Oghazi, “Literature Review on Industrial Digital Platforms: A Business Model Perspective and Suggestions for Future Research,” Technol. Forecast. Soc. Chang., vol. 194, no. September, p. 122606, 2023, doi: 10.1016/j.techfore.2023.122606.
A. Rahman et al., “A Systematic Literature Review on the Impact of Generative AI in Digital Marketing: Advancements , Opportunities , and Challenges,” Comput. Mater. Contin., vol. 87, no. 3, p. 11, 2026, doi: 10.32604/cmc.2026.071029.
T. Zhu and M. Z. A. Rozan, “AI adoption in E-commerce enterprises : Insights into current practices and future directions from an interview study,” PLoS One, vol. 21, no. 3, p. e0336416, 2026, doi: 10.1371/journal.pone.0336416.
H. N. A. Ali, “Advancements in Natural Language Processing : Towards Human-Like Understanding and Generation of Text by AI,” BIOS J. Inform. dan Sains, vol. 2, no. 02, pp. 129–139, 2024, doi: 10.54209/bios.v1i02.
B. Chen, Z. Zhang, N. Langrene, and S. Zhu, “Unleashing the Potential of Prompt Engineering for large Language Models,” Patterns, vol. 6, no. 6, p. 101260, 2025, doi: 10.1016/j.patter.2025.101260.
G. Palma, G. Cecchi, M. Caronna, and A. Rizzo, “Leveraging Large Language Models for Scalable and Explainable Cybersecurity Log Analysis,” J. Cybersecurity Priv., vol. 5, no. 3, p. 55, 2025, doi: 10.3390/jcp5030055.
X. Liu et al., “Prompting Frameworks for Large Language Models : A Survey,” ACM Comput. Surv., vol. 58, no. 10, pp. 1–38, 2026, doi: 10.1145/3789253.
K. Ramnath et al., “A Systematic Survey of Automatic Prompt Optimization Techniques,” in Conference on Empirical Methods in Natural Language Processing, Suzhou, China: Association for Computational Linguistics, 2025, pp. 33078–33110. doi: 10.18653/v1/2025.emnlp-main.0.
J. Dannhoferova and P. Jedlicka, “Optimizing Prompts Through AI Frameworks: A Path to More Relevant Responses,” in 27th International Scientific Conference Economic Competitiveness and Sustainability, Brno, Czech Republic: Mendel University Press, 2025, pp. 29–38. doi: 10.11118/978-80-7701-047-4-0029.
R. Murthy et al., “Promptomatix : An Automatic Prompt Optimization Framework for Large Language Models,” arXiv Prepr., vol. 2507, no. 14241, pp. 1–22, 2025, doi: 10.48550/arXiv.2507.14241.
S. P. Nagavalli, S. Tiwari, and W. Sarma, “Adaptive Prompt Engineering: Optimizing Large Language Model Outputs for Context-Aware Natural Language Processing,” World J. Adv. Eng. Technol. Sci., vol. 13, no. 01, pp. 1130–1141, 2024, doi: 10.30574/wjaets.
R. Coppola and L. Ardito, “Quality Assessment Methods for Textual Conversational Interfaces: A Multivocal Literature Review,” Information, vol. 12, no. 11, p. 437, 2024, doi: 10.3390/info12110437.
Junadhi, Agustin, L. Efrizoni, F. Okmayura, D. R. Habibie, and Muslim, “Improving Evaluation Metrics for Text Summarization : A Comparative Study and Proposal of a Novel Metric,” J. Appl. Data Sci., vol. 6, no. 2, pp. 885–896, 2025, doi: 10.47738/jads.v6i2.547.
M. Huseynli, U. Bub, and M. C. Ogbuachi, “Development of a Method for the Engineering of Digital Innovation Using Design Science Research,” Information, vol. 13, no. 12, p. 573, 2022, doi: 10.3390/info13120573.
M. A. Fathullah, A. Subbarao, A. Ahmad, and S. Muthaiyah, “Merging Qualitative Design Methods With Design Science,” Int. J. Qual. Methods, vol. 24, no. 80, pp. 1–11, 2025, doi: 10.1177/16094069251337585.
M. Soleymanibrojeni et al., “GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols,” Commun. Mater., vol. 7, no. April, p. 115, 2026, doi: 10.1038/s43246-026-01167-0.
T. Ivanova, “Ontology-Based Layered Hybrid AI-Driven Knowledge Model for Personalized E-Learning,” Mathematics, vol. 14, no. 5, p. 808, 2026, doi: 10.3390/math14050808.
M. Estevez, M. Teresa, and J. Sainz, “Market research and knowledge using Generative AI : the power of Large Language Models,” J. Innov. Knowl., vol. 10, no. 5, p. 100796, 2025, doi: 10.1016/j.jik.2025.100796.
S. Taha and R. A.-Q. Abdallah, “Leveraging Artificial Intelligence in Social Media Analysis : Enhancing Public Communication Through Data Science,” Journal. Media, vol. 6, no. 3, p. 102, 2025, doi: 10.3390/journalmedia6030102.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Information Technology and Business
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
