A Multiscale Assessment of the Impact of Perceived Safety from Street View Imagery on Street Crime
Bibliographic record
Abstract
Perceived safety of the built environment—a cognitive assessment different from emotional fear of crime—might affect the number of potential crime victims in an area and thus affect crime opportunities. The perceived safety derived from street view imagery has propelled scholars to examine its relationship with crime. The literature, however, has not addressed the related geographic scale variability issue; that is, the choice of the geographic analytical units might affect the relationship between area-based perceived safety and crime. This study explores how the relationships between street-view-derived perceived safety and both street thefts and street robberies vary by different spatial scales in Cincinnati. Results of negative binomial models show that perceived safety is positively associated with street thefts and street robberies at both the street segment and census block levels, but is negatively associated with these crimes at the census block group level. The relationship is not statistically significant at the census tract level. This variability is explained by the different freedom of avoidance behaviors in response to perceived safety, which change by geographic scale. The research further evaluates the within variance and between variance of perceived safety at different scales. Compared to between variance, within variance is smaller at both the street segment and block levels, but larger at both the block group and tract levels. This variability can be a source of model instability across multiple geographical scales. In short, the multiscale assessment shows that larger spatial units like the census tract are unsuitable for perceived safety–crime analysis.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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 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".