Measuring urban security perception in transport from social media data to inform transport network models: A case study for Milan in 2019 and New York City in 2021
Bibliographic record
Abstract
Urban security perception is a critical, yet understudied factor of the adequacy dimension of transport poverty. This study investigates the potential of geo-social media data to assess perceived security in urban transport networks across European cities. Using over one million geo-referenced X microblogging posts from Milan (2019) and 12 million from New York City (2021), we applied a multi-stage Natural Language Processing (NLP) pipeline, including emotion and sentiment analysis and a few-shot semantic classifier, to detect posts expressing fear and insecurity, particularly related to women’s urban mobility. These indicators were spatially aggregated and compared against reference datasets on security perception and reported crimes. Results reveal distinct spatial patterns: Milan exhibited centralised posting with sparse, artefact-prone peripheral signals, while New York City showed more dispersed clusters in areas like the Bronx, Brooklyn, and Queens. However, correlations with ground-truth security data were consistently weak (Pearson’s r < 0.07), limiting social media’s reliability as a proxy for city-wide perceptions. Supplementary analysis of geo-referenced Google Maps reviews in Milan identified higher relevance of perceived security concerns in specific place types, such as parks and public transport locations, but revealed low overall confidence scores using the social media-based models. While geo-social media offer scalable, low-cost insights, limitations in spatial granularity, platform-dependent posting behavior, and demographic bias underscore the need for refined methodologies and multimodal data integration in future research.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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".