Developing Personalized Marketing Service Using Generative AI
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
In today’s world, the development of social network services (SNS) like Facebook and Instagram has enabled consumers to acquire information about products through various channels. The acquisition of diverse information has led to a diversification in consumer preferences and requirements. As consumer preferences diversify and online channels expand, there is an increasing need for companies to provide personalized marketing. Among the means of personalized marketing, personalized marketing messages are a key tool that can enhance customer engagement. However, a limitation of personalized marketing message services is the cost issue associated with manually writing individual marketing messages for personalization. To solve this problem, when developing automated technology for personalized marketing messages, there were concerns about the complexity of model development and the quality of messages generated automatically. In this study, we propose the Persuasive Message Intelligence (PMI) service, which utilizes the recently prominent Large Language Model for automated individual personalized marketing messages. PMI generates marketing messages through prompt engineering based on the theory of persuasion in marketing and prior research on AI-generated messages, and validates the elements of prompts through surveys. The trial and error of researchers presented in this study, along with the know-how and rules of prompt engineering, will serve as guidelines for those who wish to develop services through prompts in the future.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The various related products recommended by AI-personalized recommendation can broaden consumers' consideration sets, satisfying their need for more information [121].”
From The Impact of AI-Personalized Recommendations on Clicking Intentions: Evidence from Chinese E-Commerce (2025) · cites this paper as [121]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faul, F., Erdfelder, E., Lang, A.-G., & Buchner, A. (2007) · Behavior Research Methods · doi:10.3758/bf03193146 · Cited by 65,971 · cited 1×
“The aim of the regression analysis was to investigate the correlations between variables and to understand the extent and direction of the impact of independent variables on dependent variables [20].”
Wu, T., Terry, M., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517582 · Cited by 483 · cited 1×
“The System Prompt, on the other hand, establishes the basic structure, format, and rules for generating the message [12], [13], [14].”
BackgroundGetting Too Personal: Reactance to Highly Personalized Email Solicitations
White, T. B., Zahay, D. L., Thorbjørnsen, H., & Shavitt, S. (2008) · Marketing Letters · doi:10.1007/s11002-007-9027-9 · Cited by 365 · cited 1×
“The sample size of 300 respondents exceeds the minimum sample size required for statistical analysis in academic research, as verified by the Gpower program [19].”
MethodAli, R., Tang, O. Y., Connolly, I. D., Fridley, J. S., Shin, J. H., Zadnik Sullivan, P. L., Cielo, D., Oyelese, A. A., Doberstein, C. E., Telfeian, A. E., et al. (2023) · Neurosurgery · doi:10.1227/neu.0000000000002551 · Cited by 354 · cited 2×
“OpenAI’s GPT-4 model demonstrates superior performance even when compared to the latest Large Language Models like Google’s Bard and Meta’s LLAMA2 models [9], [10], [11].”
MethodThe potential of generative AI for personalized persuasion at scale
Matz, S. C., Teeny, J. D., Vaid, S. S., Peters, H., Harari, G. M., & Cerf, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-53755-0 · Cited by 315 · cited 3×
“The format and content of these questions have been adapted based on insights from previous studies [8].”
BackgroundMethodInfluentialThe Potential of Generative AI for Personalized Persuasion at Scale
Matz, S., Teeny, J., Vaid, S. S., Peters, H., Harari, G. M., & Cerf, M. (2023) · doi:10.31234/osf.io/rn97c · Cited by 312
Consumer Responses to AI-Generated Charitable Giving Ads
Arango, L., Singaraju, S. P., & Niininen, O. (2023) · Journal of Advertising · doi:10.1080/00913367.2023.2183285 · Cited by 243 · cited 1×
“In the context of donations, it was found that advertisements generated by AI, particularly those featuring AI-generated images of children, negatively impacted donation intentions, mediated through empathy, anticipated guilt, and emotional recognition [5].”
BackgroundBlack-Box Prompt Optimization: Aligning Large Language Models without Model Training
Cheng, J., Liu, X., Zheng, K., Ke, P., Wang, H., Dong, Y., Tang, J., & Huang, M. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.176 · Cited by 197
Artificial Intelligence and Persuasion: A Construal-Level Account
Kim, T. W., & Duhachek, A. (2020) · Psychological Science · doi:10.1177/0956797620904985 · Cited by 190 · cited 3×
“The third element was based on research findings that the more specific the reasons for purchasing a product are in an advertising marketing message, the more persuasive the message becomes [6].”
BackgroundInfluentialSelf-citationKarinshak, E., Liu, S. X., Park, J. S., & Hancock, J. T. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579592 · Cited by 167 · cited 1×
“The study proposes best practices for evaluating the generative output of large language models and guidelines for public health professionals on using AI systems [7].”
BackgroundPerformance of the pre-trained large language model GPT-4 on automated short answer grading
Kortemeyer, G. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00147-y · Cited by 100 · cited 2×
“OpenAI’s GPT-4 model demonstrates superior performance even when compared to the latest Large Language Models like Google’s Bard and Meta’s LLAMA2 models [9], [10], [11].”
MethodLim, S., & Schmälzle, R. (2023) · Frontiers in Communication · doi:10.3389/fcomm.2023.1129082 · Cited by 89 · cited 1×
“The System Prompt, on the other hand, establishes the basic structure, format, and rules for generating the message [12], [13], [14].”
BackgroundDehnert, M., & Mongeau, P. A. (2022) · Human Communication Research · doi:10.1093/hcr/hqac006 · Cited by 86 · cited 5×
“The study concludes that AI-generated messages are perceived by humans through a heuristic process, and for these messages to be persuasive, AI must provide messages with high relevance, usability, and accessibility [4].”
BackgroundInfluentialOn Data Reliability Assessment in Accounting Information Systems
Krishnan, R., Peters, J. M., Padman, R., & Kaplan, D. (2005) · Information Systems Research · doi:10.1287/isre.1050.0063 · Cited by 78 · cited 1×
“BPMN serves as a pivotal tool in visualizing the flow of processes in diagrammatic form, thereby facilitating a clear understanding of the operational workflow in businesses [15], [16], [17].”
Privacy Concerns in Personalized Advertising Effectiveness on Social Media
Lina, L. F., & Setiyanto, A. (2021) · SRIWIJAYA INTERNATIONAL JOURNAL OF DYNAMIC ECONOMICS AND BUSINESS · doi:10.29259/sijdeb.v1i2.147-156 · Cited by 48 · cited 1×
“As a result, consumers exhibit a greater propensity to engage in purchasing behavior in response to personalized or targeted advertisements rather than traditional mass advertising [2].”
BackgroundDesigning questionnaires: healthcare survey to compare two different response scales
Dell‐Kuster, S., Sanjuan, E. C., Todorov, A., Weber, H., Heberer, M., & Rosenthal, R. (2014) · BMC Medical Research Methodology · doi:10.1186/1471-2288-14-96 · Cited by 46 · cited 3×
“Regarding independence, the item groups concerning AI creation awareness satisfy the criterion of independence [23].”
BackgroundInfluentialImpact of Personalized Social Media Advertising on Online Impulse Buying Behavior
Aslam, H., Rashid, M., & Chaudhary, N. (2021) · SEISENSE Business Review · doi:10.33215/sbr.v1i3.660 · Cited by 44 · cited 1×
“Specifically, online advertising, which is often more targeted, elicits a more active intent to purchase [3].”
Background10 points versus 11 points? Effects of Left-right Scale Design in a Cross-national Perspective
Zuell, C., & Scholz, E. (2016) · Social Science Open Access Repository (GESIS – Leibniz Institute for the Social Sciences) · Cited by 10
Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer GradingPreprint
Kortemeyer, G. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.09338 · Cited by 5 · cited 2×
“OpenAI’s GPT-4 model demonstrates superior performance even when compared to the latest Large Language Models like Google’s Bard and Meta’s LLAMA2 models [9], [10], [11].”
MethodManaging knowledge sharing — Case study of a consulting firm
Szirtes, T. (2011) · Society and Economy · doi:10.1556/socec.2011.0009 · Cited by 4 · cited 3×
“Additionally, the reasons for recommending specific products were detailed, and information perceived as less invasive to personal privacy, such as age, gender, and purchase history [17], was utilized to create personalized messages.”
BackgroundMethodCustomer Satisfaction and Service Experience in Big Data Analytics for Automotive Service Advisor
Samsudin, S. N., Abdullah, B. B., & Yusoff, N. (2022) · IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS) · doi:10.1109/i2cacis54679.2022.9815482 · Cited by 4 · cited 1×
“As for homoscedasticity, the Levene’s test for equality of variances conducted in SPSS25 yielded an F-value of 0.000 and a P-value of 0.946, satisfying the condition of P > = 0.5 and thus supporting the assumption of homoscedasticity [24].”
ResultInfluentialWill Social Media and Its Consumption Converge or Diverge Global Consumer Culture?
Kang, Y., & Yang, K. C. C. (2022) · IGI Global eBooks · doi:10.4018/978-1-6684-6287-4.ch101 · Cited by 1
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
Cheng, J., Liu, X., Zheng, K., Ke, P., Wang, H., Dong, Y., Tang, J., & Huang, M. (2023) · arXiv · doi:10.48550/arxiv.2311.04155
Research works printed but not linked: 3
- Qian, Performance evaluation on human-machine teaming augmented machine translation enabled by GPT-4, 20
- Ballentine, 2016, Using process modeling notation to map the buying and selling of complex software solutions: A qualitative study’s implications for practice and pedagogy, Tech. Commun., 63, 212
- 2023, Prompt-Engineering
Cited by
Yin, J., Qiu, X., & Wang, Y. (2025) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer20010021 · Cited by 103
Consumer segmentation with large language models
Li, Y., Liu, Y., & Yu, M. (2024) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.104078 · Cited by 49
Market research and knowledge using Generative AI: the power of Large Language Models
Estévez, M., Ballestar, M. T., & Sáinz, J. (2025) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2025.100796 · Cited by 43
Papageorgiou, G., Sarlis, V., Μaragoudakis, M., & Tjortjis, C. (2024) · Applied Sciences · doi:10.3390/app14188259 · Cited by 44
Sun, H., Xie, P., & Sun, Y. (2025) · Journal of Advertising Research · doi:10.1080/00218499.2025.2462405 · Cited by 39
Metadata
- Authors
- Lee, G. H., Lee, K. J., Jeong, B., & Kim, T.
- Affiliations
- Kyung Hee University (KR)
- Department of Big Data Analytics, Kyung Hee University, Seoul, South Korea
- Venue
- IEEE Access
- Published
- 2024
- Volume
- 12
- Pages
- 22394-22402
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4391547586
- Cited by
- 44
- References
- 22
- Citations by year
- 2026: 15 · 2025: 21 · 2024: 8
- FWCI
- 6.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- BK21 Fostering Outstanding Universities for Research
- Ministry of Education (MOE), South Korea
- National Research Foundation of Korea
- Topics
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Social Sciences › Business, Management and Accounting › Marketing › Digital Marketing and Social Media
- Social Sciences › Business, Management and Accounting › Marketing › Marketing and Advertising Strategies
- Keywords
- personalized marketing, generative AI, large language models, prompt engineering, persuasive messages, customer engagement, consumer preferences
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.