Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering
IntroductionThis 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.MethodWe used prompt engineering to generate awareness messages about folic acid and compare...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-05-01
|
Series: | Frontiers in Communication |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcomm.2023.1129082/full |
_version_ | 1797819816804876288 |
---|---|
author | Sue Lim Ralf Schmälzle |
author_facet | Sue Lim Ralf Schmälzle |
author_sort | Sue Lim |
collection | DOAJ |
description | IntroductionThis 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.MethodWe 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.ResultsThe 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.DiscussionOverall, these results demonstrate the potential of large language models for message generation. Theoretical, practical, and ethical implications are discussed. |
first_indexed | 2024-03-13T09:28:13Z |
format | Article |
id | doaj.art-6a757f19f0364218ab130ddb7ff69a0b |
institution | Directory Open Access Journal |
issn | 2297-900X |
language | English |
last_indexed | 2024-03-13T09:28:13Z |
publishDate | 2023-05-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Communication |
spelling | doaj.art-6a757f19f0364218ab130ddb7ff69a0b2023-05-26T04:31:52ZengFrontiers Media S.A.Frontiers in Communication2297-900X2023-05-01810.3389/fcomm.2023.11290821129082Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineeringSue LimRalf SchmälzleIntroductionThis 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.MethodWe 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.ResultsThe 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.DiscussionOverall, these results demonstrate the potential of large language models for message generation. Theoretical, practical, and ethical implications are discussed.https://www.frontiersin.org/articles/10.3389/fcomm.2023.1129082/fullhealth communicationmessage generationartificial intelligenceprompt engineeringsocial mediafolic acid (FA) |
spellingShingle | Sue Lim Ralf Schmälzle Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering Frontiers in Communication health communication message generation artificial intelligence prompt engineering social media folic acid (FA) |
title | Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering |
title_full | Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering |
title_fullStr | Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering |
title_full_unstemmed | Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering |
title_short | Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering |
title_sort | artificial intelligence for health message generation an empirical study using a large language model llm and prompt engineering |
topic | health communication message generation artificial intelligence prompt engineering social media folic acid (FA) |
url | https://www.frontiersin.org/articles/10.3389/fcomm.2023.1129082/full |
work_keys_str_mv | AT suelim artificialintelligenceforhealthmessagegenerationanempiricalstudyusingalargelanguagemodelllmandpromptengineering AT ralfschmalzle artificialintelligenceforhealthmessagegenerationanempiricalstudyusingalargelanguagemodelllmandpromptengineering |