ALF-Score+ - Personalization of a Predictive Network-Based Walkability Scoring System
Bibliographic record
Abstract
Measuring environments around us (cities, roads, social environments) is crucial to understand human behaviour and help predict how aspects of environment influence behaviour and health. Walkability is one measure of environment used to predict health. Walkability combines aspects of environment (population, roads, amenities) into a single score. Existing measures are often one-size-fits-all with very limited personalization. In our previous work, we defined Active Living Feature Score, ALF-Score, a novel approach to measure network-based walkability. ALF-Score uses road network structures and points of interest to generate models capable of estimating walkability for any point on map. One of ALF-Score's contributions was the inclusion of user opinions to partially address the different perception among individuals and help derive a more personalized walkability score. Here, we take this personalization much further by introducing ALF-Score+ which uses individual user demographics (age, gender, ...) grouped using k-means and t-distributed stochastic neighbor embedding to create clusters based on individuals’ demographic characteristics. Each cluster is treated as a single profile representing a subset of users. Cluster profiles are added into our pipelines to generate profile-specific network-based walkability models. Results show strong variability among scores generated for each cluster profile with a clear variation in walkability generated for different users within same clusters. ALF-Score+ maintains an accuracy of 90.48% on average showing improvement compared to ALF-Score. We found strong association between cluster profiles' demographics and their scores. ALF-Score+ shows promising results providing personalized walkability based on cluster profiles, instead of a one-size-fits-all approach used by other walkability measures.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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) | 0.001 | 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".