Large language models for promoting physical activity: a review of experiential and behavioral outcomes, social roles, and human-likeness in persuasive LLMs - Report - MDSpire
Advertisement
Large language models for promoting physical activity: a review of experiential and behavioral outcomes, social roles, and human-likeness in persuasive LLMs
Clinical Report: Exploring the Role of Large Language Models in Encouraging Physical Activity
Overview
This review examines the role of Large Language Models (LLMs) in promoting physical activity through conversational agents, drawing on findings from 13 studies. It identifies positive user engagement outcomes but notes limited evidence for sustained impacts on objectively measured physical activity.
Background
The integration of conversational agents in health interventions is gaining traction, particularly for promoting physical activity. These agents, especially those powered by LLMs, offer more human-like interactions compared to traditional rule-based systems. Understanding their effectiveness and user experience is crucial as physical inactivity poses significant health risks globally, as highlighted by the WHO.
Data Highlights
No numerical data presented in the article, which limits the ability to quantify the effectiveness of LLMs in promoting physical activity.
Key Findings
LLM-based conversational agents can enhance user engagement in physical activity promotion, as evidenced by multiple studies.
Evidence for a direct and sustained impact on objectively measured physical activity is limited, according to the reviewed literature.
LLMs can assume various social roles, affecting relational dynamics with users.
Users tend to anthropomorphize LLMs, which may enhance emotional investment but also lead to over-reliance.
Ethical concerns arise regarding the persuasive capabilities of LLMs and the redistribution of agency, as discussed in the literature.
Clinical Implications
Healthcare professionals should be aware of the potential benefits and limitations of LLM-based conversational agents in promoting physical activity, as indicated by the findings. Ethical considerations regarding user expectations and agency should be addressed in the design and implementation of these technologies.
Conclusion
The review highlights the promise of LLMs in health behavior change while emphasizing the need for further research to understand their long-term efficacy and ethical implications, as identified in the reviewed studies.
