The potential and limitations of large language models in identification of the states of motivations for facilitating health behavior change

Michelle Bak, Jessie Chin

Research output: Contribution to journalArticlepeer-review

Abstract

Importance

The study highlights the potential and limitations of the Large Language Models (LLMs) in recognizing different states of motivation to provide appropriate information for behavior change. Following the Transtheoretical Model (TTM), we identified the major gap of LLMs in responding to certain states of motivation through validated scenario studies, suggesting future directions of LLMs research for health promotion.

Objectives

The LLMs-based generative conversational agents (GAs) have shown success in identifying user intents semantically. Little is known about its capabilities to identify motivation states and provide appropriate information to facilitate behavior change progression.

Materials and Methods

We evaluated 3 GAs, ChatGPT, Google Bard, and Llama 2 in identifying motivation states following the TTM stages of change. GAs were evaluated using 25 validated scenarios with 5 health topics across 5 TTM stages. The relevance and completeness of the responses to cover the TTM processes to proceed to the next stage of change were assessed.

Results

3 GAs identified the motivation states in the preparation stage providing sufficient information to proceed to the action stage. The responses to the motivation states in the action and maintenance stages were good enough covering partial processes for individuals to initiate and maintain their changes in behavior. However, the GAs were not able to identify users’ motivation states in the precontemplation and contemplation stages providing irrelevant information, covering about 20%-30% of the processes.

Discussion

GAs are able to identify users’ motivation states and provide relevant information when individuals have established goals and commitments to take and maintain an action. However, individuals who are hesitant or ambivalent about behavior change are unlikely to receive sufficient and relevant guidance to proceed to the next stage of change.

Conclusion

The current GAs effectively identify motivation states of individuals with established goals but may lack support for those ambivalent towards behavior change.
Original languageEnglish (US)
Article numberocae057
JournalJournal of the American Medical Informatics Association
DOIs
StateE-pub ahead of print - Mar 25 2024

Keywords

  • large language models
  • behavior change
  • motivations
  • health promotion
  • Llama 2
  • Google Bard
  • ChatGPT

Fingerprint

Dive into the research topics of 'The potential and limitations of large language models in identification of the states of motivations for facilitating health behavior change'. Together they form a unique fingerprint.

Cite this