Persuasion and Behavior Change in ChatGPT-Based Dietary Management
Bibliographic record
Abstract
The emergence of Large Language Models (LLMs) such as ChatGPT has led to applications like digital interventions across diverse domains, including digital dietary behavior change interventions (DBCIs). While various AI-based apps, web-based platforms, and gamified mobile applications have shown their effectiveness as persuasive tools for promoting dietary behavioral change, the capabilities of ChatGPT in this domain remain unexplored. This study examines qualitative responses from users informing the different persuasive strategies employed by ChatGPT in dietary management. Through a mixed study, we evaluated ChatGPT's overall persuasiveness for diet management and user insights on the strengths and gaps of its use and persuasive capabilities. We recruited 17 ChatGPT-4 users and engaged them in interactions with AI-generated meal plans. Subsequently, they provided feedback through interviews and a perceived persuasiveness scale questionnaire. Our findings reveal that users generally perceive ChatGPT as persuasive in promoting healthy eating behaviors (p<.006). Thematic analysis emerging from our interview transcripts showed that ChatGPT has implemented some persuasive strategies while indicating the need to include additional ones e.g. self-monitoring, reminders, and trustworthiness. Based on our findings, we contribute to the field by providing recommendations for developers on integrating additional persuasive strategies while considering the ethical implications of using LLMs for dietary management.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.048 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".