Predicting Prediabetes Through Facebook Postings: Protocol for a Mixed-Methods Study
Bibliographic record
Abstract
BACKGROUND: The field of infodemiology uses health care trends found in public networks, such as social media, to track and quantify the spread of disease. Type 2 diabetes is on the rise worldwide, and social media may be useful in identifying prediabetes through behavior exhibited through social media platforms such as Facebook and thus in designing and administering early interventions and containing further progression of the disease. OBJECTIVE: This pilot study is designed to investigate the social media behavior of individuals with prediabetes, before and after diagnosis. Pre- and postdiagnosis Facebook content (posts) of such individuals will be used to create a taxonomy of prediabetes indicators and to identify themes and factors associated with an actual diagnosis of prediabetes. METHODS: This is a single-center exploratory retrospective study that examines 20 adults with prediabetes. The investigators will code Facebook posts 3 months before through 3 months after prediabetes diagnosis. Data will be analyzed using both qualitative content analysis methodology as well as quantitative methodology to characterize participants and compare their posts pre- and postdiagnosis. RESULTS: The project was funded for 2015-2018, and enrollment will be completed by the end of 2018. Data coding is currently under way and the first results are expected to be submitted for publication in 2019. Results will include both quantitative and qualitative data about participants and the similarities and differences between coded social media posts. CONCLUSIONS: This pilot study is the first step in creating a taxonomy of social media indicators for prediabetes. Such a taxonomy would provide a tool for researchers and health care professionals to use social media postings for identifying those at greater risk of having prediabetes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/10720.
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 | 0.080 | 0.073 |
| Meta-epidemiology (narrow) | 0.005 | 0.005 |
| Meta-epidemiology (broad) | 0.006 | 0.005 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.007 | 0.004 |
| Scholarly communication | 0.005 | 0.004 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.007 | 0.009 |
| Insufficient payload (model declined to judge) | 0.097 | 0.026 |
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".