Evaluating the effectiveness of artificial intelligence‐based tools in detecting and understanding sleep health misinformation: Comparative analysis using Google Bard and <scp>OpenAI ChatGPT</scp>‐4
Bibliographic record
Abstract
This study evaluates the performance of two major artificial intelligence-based tools (ChatGPT-4 and Google Bard) in debunking sleep-related myths. More in detail, the present research assessed 20 sleep misconceptions using a 5-point Likert scale for falseness and public health significance, comparing responses of artificial intelligence tools with expert opinions. The results indicated that Google Bard correctly identified 19 out of 20 statements as false (95.0% accuracy), not differing from ChatGPT-4 (85.0% accuracy, Fisher's exact test p = 0.615). Google Bard's ratings of the falseness of the sleep misconceptions averaged 4.25 ± 0.70, showing a moderately negative skewness (-0.42) and kurtosis (-0.83), and suggesting a distribution with fewer extreme values compared with ChatGPT-4. In assessing public health significance, Google Bard's mean score was 2.4 ± 0.80, with skewness and kurtosis of 0.36 and -0.07, respectively, indicating a more normal distribution compared with ChatGPT-4. The inter-rater agreement between Google Bard and sleep experts had an intra-class correlation coefficient of 0.58 for falseness and 0.69 for public health significance, showing moderate alignment (p = 0.065 and p = 0.014, respectively). Text-mining analysis revealed Google Bard's focus on practical advice, while ChatGPT-4 concentrated on theoretical aspects of sleep. The readability analysis suggested Google Bard's responses were more accessible, aligning with 8th-grade level material, versus ChatGPT-4's 12th-grade level complexity. The study demonstrates the potential of artificial intelligence in public health education, especially in sleep health, and underscores the importance of accurate, reliable artificial intelligence-generated information, calling for further collaboration between artificial intelligence developers, sleep health professionals and educators to enhance the effectiveness of sleep health promotion.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.019 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".