Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Introduction: This study introduces and examines the potential of an AI system to generate health awareness messages. The topic of folic acid, a vitamin that is critical during pregnancy, served as a test case. Method: We used prompt engineering to generate awareness messages about folic acid and compared them to the most retweeted human-generated messages via human evaluation with an university sample and another sample comprising of young adult women. We also conducted computational text analysis to examine the similarities between the AI-generated messages and human generated tweets in terms of content and semantic structure. Results: The results showed that AI-generated messages ranked higher in message quality and clarity across both samples. The computational analyses revealed that the AI generated messages were on par with human-generated ones in terms of sentiment, reading ease, and semantic content. Discussion: Overall, these results demonstrate the potential of large language models for message generation. Theoretical, practical, and ethical implications are discussed.
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.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
VADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087
Flesch, R. (1948) · Journal of Applied Psychology · doi:10.1037/h0057532 · Cited by 5,391 · cited 2×
“An analysis of text readability statistics (Flesch, 1948) showed that AI-generated messages were as easy to read, if not easier to read, compared to the human-generated messages ( m Flesch − ScoreAI = 68.4, m Flesch − Scorehuman = 63.4; n.s. ).”
BackgroundInfluentialActual Causes of Death in the United States, 2000
Mokdad, A. H. (2004) · JAMA · doi:10.1001/jama.291.10.1238 · Cited by 5,211 · cited 1×
“The need to communicate about health is clear, compelling, and constantly high: About 60% of worldwide deaths and a large share of the global burden of disease are due to preventable factors (Mokdad et al., 2004; Giles, 2011; Ahmad and Anderson, 2021).”
BackgroundLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352 · cited 3×
“As prompting can significantly influence the generated messages (Liu et al., 2023), prompts were crafted based on the sentence structure of the most retweeted messages.”
BackgroundMethodProlific.ac—A subject pool for online experiments
Palan, S., & Schitter, C. (2018) · Journal of Behavioral and Experimental Finance · doi:10.1016/j.jbef.2017.12.004 · Cited by 3,450
The Elaboration Likelihood Model of Persuasion
Petty, R. E., & Cacioppo, J. T. (1986) · Communication and Persuasion · doi:10.1007/978-1-4612-4964-1_1 · Cited by 3,202
Building machines that learn and think like people
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x16001837 · Cited by 2,550
Building Machines That Learn and Think Like People
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016) · arXiv · doi:10.48550/arxiv.1604.00289 · Cited by 2,550
Does tailoring matter? Meta-analytic review of tailored print health behavior change interventions
Noar, S. M., Benac, C. N., & Harris, M. S. (2007) · Psychological Bulletin · doi:10.1037/0033-2909.133.4.673 · Cited by 2,136
Advances in natural language processing
Hirschberg, J., & Manning, C. D. (2015) · Science · doi:10.1126/science.aaa8685 · Cited by 1,712
Neuroscience-Inspired Artificial Intelligence
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017) · Neuron · doi:10.1016/j.neuron.2017.06.011 · Cited by 1,557 · cited 2×
“DLfueled applications are integrated in every cell phone and computer (Schmidhuber, 2015; Hassabis et al., 2017; Chollet, 2021).”
BackgroundResultAn Explication of Social Norms
Lapinski, M. K., & Rimal, R. N. (2005) · Communication Theory · doi:10.1111/j.1468-2885.2005.tb00329.x · Cited by 1,424 · cited 1×
“…effects (e.g., emotional appeals; Nabi et al., 2020; Turner and Rains, 2021, message tailoring; Noar et al., 2007), information processing (e.g, Elaboration Likelihood Model; Petty et al., 1986), and persuasion (e.g., source factors; O’Keefe, 2015, social norms; Lapinski and Rimal, 2005) exist.”
BackgroundHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266 · cited 2×
“Next, top-k and top-p sampling strategies were used in combination in order to allow for variation in generated text while preventing words with low calculated probabilities from being selected (top_k=40, top_p=0.9; Fan et al., 2018; von Platen, 2020).”
MethodInfluentialHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Bender, E. M., & Koller, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.463 · Cited by 1,082 · cited 2×
“Although many limitations still exist (Bender and Koller, 2020), recent advancements in this area are very relevant for communication science and have many theoretical implications.”
Backgroundtopicmodels : An R Package for Fitting Topic Models
Grün, B., & Hornik, K. (2011) · Journal of Statistical Software · doi:10.18637/jss.v040.i13 · Cited by 1,072
Gatt, A., & Krahmer, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5477 · Cited by 776
CTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751
AI-Mediated Communication: Definition, Research Agenda, and Ethical Considerations
Hancock, J. T., Naaman, M., & Levy, K. (2020) · Journal of Computer-Mediated Communication · doi:10.1093/jcmc/zmz022 · Cited by 658
In Search of Mechanisms: Discoveries across the Life Sciences
Craver, C. F., & Darden, L. (2013) · doi:10.7208/chicago/9780226039824.001.0001 · Cited by 531
Enhancing promotional strategies within social marketing programs: use of Web 2.0 social media
Thackeray, R., Neiger, B. L., Hanson, C. L., & McKenzie, J. F. (2008) · Health Promotion Practice · doi:10.1177/1524839908325335 · Cited by 530 · cited 1×
“Health researchers have already begun examining how to leverage this phenomenon on social media to expand the research of health messages (Thackeray et al., 2008; Kim, 2015; Wang et al., 2019).”
BackgroundHealth communication campaigns and their impact on behavior
Snyder, L. B. (2007) · Journal of Nutrition Education and Behavior · doi:10.1016/j.jneb.2006.09.004 · Cited by 397
All the News That’s Fit to Fabricate: AI-Generated Text as a Tool of Media Misinformation
Kreps, S., McCain, R. M., & Brundage, M. (2022) · Journal of Experimental Political Science · doi:10.1017/xps.2020.37 · Cited by 360 · cited 1×
“Examples of existing issues include bots in the political domain (which spread misinformation), online troll farms (which stoke conflict), or general misuse of persuasive technologies for target advertising or mood, and emotion intervention (Solaiman et al., 2019; Kreps et al., 2020).”
BackgroundRelease Strategies and the Social Impacts of Language Models
Solaiman, I., Brundage, M., Clark, J., Askell, A., Herbert-Voss, A., Wu, J., Radford, A., Krueger, G., Kim, J. W., Kreps, S., et al. (2019) · arXiv · doi:10.48550/arxiv.1908.09203 · Cited by 292 · cited 2×
“Examples of existing issues include bots in the political domain (which spread misinformation), online troll farms (which stoke conflict), or general misuse of persuasive technologies for target advertising or mood, and emotion intervention (Solaiman et al., 2019; Kreps et al., 2020).”
BackgroundKarinshak, 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×
“There is already evidence of researchers leveraging LLMs for persuasive message generation within health communication (Karinshak et al., 2023; Zhou et al., 2023).”
BackgroundThe BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
Laurençon, H., Saulnier, L., Wang, T., Akiki, C., del Moral, A. V., Scao, T. L., Von Werra, L., Mou, C., Ponferrada, E. G., Nguyen, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.03915 · Cited by 93 · cited 2×
“, 2022) including, for example, the Wikipedia and the Semantic Scholar Open Research Corpus (Laurençon et al., 2022).”
BackgroundWhat makes cancer information viral on social media?
Wang, X., Chen, L., Shi, J., & Peng, T.-Q. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2018.12.024 · Cited by 93
Factors contributing to the success of folic acid public health campaigns
Rofail, D., Colligs, A., Abetz, L., Lindemann, M., & Maguire, L. (2012) · Journal of Public Health · doi:10.1093/pubmed/fdr048 · Cited by 60
Harnessing Artificial Intelligence for Health Message Generation: The Folic Acid Message Engine
Schmälzle, R., & Wilcox, S. (2022) · Journal of Medical Internet Research · doi:10.2196/28858 · Cited by 43 · cited 7×
“In order to generate topic-focused (i.e. about Folic Acid) social media messages, Schmälzle and Wilcox (2022) used a fine-tuning strategy.”
BackgroundMethodInfluentialSelf-citation
Cited by
Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial
Meskó, B. (2023) · Journal of Medical Internet Research · doi:10.2196/50638 · Cited by 709
“One study introduced the potential of an AI system to generate health awareness messages through prompt engineering [11].”
Prompt Engineering Paradigms for Medical Applications: Scoping Review
Zaghir, J., Naguib, M., Bjelogrlic, M., Névéol, A., Tannier, X., & Lovis, C. (2024) · Journal of Medical Internet Research · doi:10.2196/60501 · Cited by 143
Chow, J. C. L., & Li, K. (2024) · JMIR Bioinformatics and Biotechnology · doi:10.2196/64406 · Cited by 75
Developing Personalized Marketing Service Using Generative AI
Lee, G. H., Lee, K. J., Jeong, B., & Kim, T. (2024) · IEEE Access · doi:10.1109/access.2024.3361946 · Cited by 44
“The System Prompt, on the other hand, establishes the basic structure, format, and rules for generating the message [12], [13], [14].”
BackgroundThe Health Communications Assessment Checklist: a teaching tool for uncovering bias in the age of AI
Ofrane, R. H., Canada, T., & Birnbaum, A. S. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1872506
Metadata
- Authors
- Lim, S., & Schmälzle, R.
- Venue
- Frontiers in Communication
- Publisher
- Frontiers Media SA
- Published
- 2023-05-26
- Volume
- 8
- ISSN
- 2297-900X (ISSN-L)
- OpenAlex
- W4378387269
- Cited by
- 89
- References
- 34
- FWCI
- 3.08
- Type
- journal article
- Language
- en
- Open access
- gold
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.