Impacts of perceived safety and beauty of park environments on time spent in parks: Examining the potential of street view imagery and phone-based GPS data
Bibliographic record
Abstract
Much research shows that urban parks can benefit human health. Research has shown that perceptions of park environments are an important determinant of park usage. Most perception-based research collects data through costly and time-consuming survey approaches, which limits data collection on a large scale. Google Street View (GSV) imagery presents a cost-effective source for deriving perceptions of the park environment: for large parks, GSV images are available on both peripheral roads and internal roads; for small parks, majorly covered by grassland, GSV images on peripheral roads can capture their general built environment. Additionally, the available Global Positioning System (GPS) incorporated into cellular phones enables researchers to measure how long people stay in parks conveniently by checking the time of the first and last GPS points in a park. Taking Chicago as the case study, this research introduces GSV images and the SafeGraph phone-based GPS dataset to study the association between perceptions of park environments and time spent in parks, which is rarely explored by previous studies. We derive both perceived safety and beauty of park environments using GSV images in 2018 and machine-learning Support Vector Machine models trained by a crowdsourcing dataset on human perception of environments. Time spent in each park is obtained from SafeGraph data in 2018. We build negative binomial regression models to explore the relationship between perception variables and time spent in parks. Results show that higher levels of both perceived safety and beauty are positively associated with increased time, and adding perception variables can improve the model performance. It benefits urban planners in designing a better park environment in support of park usage.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 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".