Tracking the Debate: Geo‐Temporal Sentiment Analysis of Community Water Fluoridation on ‘X’ (Formerly Twitter) With Five‐Year Forecast
Bibliographic record
Abstract
OBJECTIVES: This study examined country-level geo-temporal sentiment trends in community water fluoridation (CWF) discussions on 'X' from 2014 to 2023 and generated a five-year forecast to anticipate future shifts. METHODS: Sentiment analysis was conducted using the VADER 'SentimentIntensityAnalyzer', with polarity thresholds defined as negative (< -0.05), neutral (-0.05 to +0.05) and positive (> +0.05). Data were collected via the 'X' API and examined for sentiment distribution, country-level geo-temporal patterns based on user location information, and engagement metrics (likes, retweets, replies). Ethical approval was obtained, and only publicly available data were analysed in compliance with the platform's terms of service. Limitations include restriction to English-language tweets and the non-representativeness and demographic biases of 'X' users compared with national populations. RESULTS: Of 72 309 original tweets analysed, 37.4% were negative, 34.4% positive and 28.2% neutral. Countries with low tweet volumes (e.g., Venezuela, Cyprus, Croatia, Pakistan, Vietnam) showed predominantly positive sentiment. In contrast, high-volume countries (the US, Canada, Australia, Brazil and the United Kingdom) displayed mixed sentiment without a clear majority. Predictive modelling indicated a modest shift toward less positive sentiment polarity over the next 5 years, with average polarity projected to decrease from 0.43 in 2024 to 0.38 in 2028. Supplementary analysis of more recent tweets (Jan 2024-Aug 2025) provided further insight into emerging patterns, broadly consistent with the projected trends. CONCLUSIONS: CWF discourse on 'X' is polarised and varies across countries and time. The expected decline in positivity underscores the need for tailored country-specific public health communication strategies to strengthen engagement and counter misinformation.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".