Are Crime and Collective Emotion Interrelated? A “Broken Emotion” Conjecture from Community Twitter Posts
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
A neighborhood’s social cohesion, referring to the emotional and social connection of people within it, tends to have an influential impact on its crime level. Traditional approaches to measuring social cohesion and collective efficacy are mostly interviews and surveys, which are usually costly in time, money, and other resources. Big social media data provides us with a new and cost-effective source of such information. We believe the combination of spatial and contextual information of geotagged Twitter posts (tweets) can gauge the residents’ collective emotions in a neighborhood. The positivity and negativity of these collective emotions may be used to approximate the collective efficacy of the community. Inspired by the broken window theory, we propose a broken emotion conjecture to explain the relationship between collective emotion and crime. To test this conjecture, we collected data on four types of crime (assaults, burglaries, robberies, and thefts) and all public geotagged tweets ( N = 778,901) in Cincinnati, Ohio, USA in 2013. We extracted innovative variables from tweets’ spatial and contextual information to explain community crime and enlighten new criminology theory. Results of negative binomial models show: (1) with necessary socio-economic and land-use factors controlled, the more negative the collective emotion of a neighborhood, the more the crime (except for theft); (2) however, the positivity of the collective emotion of a neighborhood does not have any statistically significant influence on crime. These correspond well with signal detection theory in psychology. The proposed broken emotion conjecture is supported with data from Cincinnati and its general applicability should be tested in other regions.
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 | 0.002 | 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 | 0.006 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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