Development of a Conversational Agent for Individuals Ambivalent About Quitting Smoking: Protocol for a Proof-of-Concept Study
Bibliographic record
Abstract
BACKGROUND: Cigarette smoking is the leading preventable cause of disease and death in the United States. Despite the availability of a plethora of evidence-based smoking cessation resources, less than one-third of individuals who smoke seek cessation services, and individuals using these services are often those who are actively contemplating quitting smoking. There is a distinct dearth of low-cost, scalable interventions to support smokers not ready to quit (ambivalent smokers). Such interventions can assist in gradually promoting smoking behavior changes in this target population until motivation to quit arises, at which time they can be navigated to existing evidence-based smoking cessation interventions. Conversational agents or chatbots could provide cessation education and support to ambivalent smokers to build motivation and navigate them to evidence-based resources when ready to quit. OBJECTIVE: The goal of our study is to test the proof-of-concept of the development and preliminary feasibility and acceptability of a smoking cessation support chatbot. METHODS: We will accomplish our study aims in 2 phases. In phase 1, we will survey 300 ambivalent smokers to determine their preferences and priorities for a smoking cessation support chatbot. A "forced-choice experiment" will be administered to understand participants' preferred characteristics (attributes) of the proposed chatbot prototype. The data gathered will be used to program the prototype. In phase 2, we will invite 25 individuals who smoke to use the developed prototype. For this phase, participants will receive an overview of the chatbot and be encouraged to use the chatbot and engage and interact with the programmed attributes and components for a 2-week period. RESULTS: At the end of phase 1, we anticipate identifying key attributes that ambivalent smokers prefer in a smoking cessation support chatbot. At the end of phase 2, chatbot acceptability and feasibility will be assessed. The study was funded in June 2022, and data collection for both phases of the study is currently ongoing. We expect study results to be published by December 2023. CONCLUSIONS: Study results will yield a smoking behavior change chatbot prototype developed for ambivalent smokers that will be ready for efficacy testing in a larger study. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/44041.
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 | 0.037 | 0.035 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.063 | 0.013 |
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".