Can Topic Modeling of Local Newspaper Texts Enhance Understanding of Neighborhood Effects on Health?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
ABSTRACT Social attributes of neighborhoods, like heritage, and low‐level social disorder, are not reflected in official metrics such as deprivation indices. However, research suggests these attributes are important for understanding spatial variations in health and social outcomes. This exploratory study investigated whether recurring themes in local newspaper articles capture meaningful social characteristics that help explain neighborhood health resilience, defined as a dearth of illness after adjusting for deprivation. Topic modeling of geo‐referenced texts identified and quantified 55 themes of commonly occurring words in Edinburgh, which capture salient neighborhood attributes. Correlations between the themes and domains of the Scottish Index of Multiple Deprivation (SIMD) were weak, suggesting that newspaper themes captured characteristics beyond those in the SIMD. Reassuringly, expected correlations were observed between crime metrics from newspapers and the SIMD domains. Stepwise regression modeling revealed theoretically plausible themes associated with neighborhood health resilience/vulnerability. Themes on heritage and community sports identity were positively associated with health resilience, whereas low‐level social disorder (e.g., littering, antisocial behavior) and “local politics” were negatively associated. This study underscores the potential of using area‐based topic modeling of newspaper texts to capture neighborhood aspects neglected in official statistics but could further explain spatial variations in neighborhood health outcomes.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.006 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it