Investigating Problem of Distracted Drivers on Louisiana Roadways
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study investigates distracted driving on Louisiana roadways, motivated by the state’s poor road safety performance and the persistent prevalence of cellphone-related distractions. Despite the potential of autonomous vehicles to reduce fatalities, distracted driving remains a critical challenge for transportation agencies. The research aimed to address four specific objectives: reviewing the quality of distracted driving crash reporting, analyzing crash severity using statistical and data mining models, investigating observable driver characteristics through roadside and in-vehicle surveys, and recommending countermeasures. The methodology combined historical crash data analysis with observational studies. Researchers analyzed approximately 60,000 crashes from a ten-year dataset, focusing on crashes where drivers were distracted by in-vehicle sources. They modeled three severity categories: fatal/severe injury, moderate/complaint injury, and property-damage only. To predict crash severity, the study employed multinomial logistic regression and the random forest data mining algorithm. Additionally, the team conducted manual roadside observations of 3,727 drivers across urban and rural intersections and segments, identifying 827 distracted drivers. For in-vehicle analysis, they collected 230 minutes of video footage from student drivers, using FaceReader software to code facial expressions and emotional valence during cellphone use. Key findings revealed that higher speed limits, curved roads, and head-on collisions were significant factors associated with distracted driving crashes. The random forest algorithm demonstrated superior predictive performance compared to multinomial logistic regression when evaluated by sensitivity and specificity. Roadside observation data indicated that gender did not significantly influence cellphone distraction, whereas age was a significant factor. Association rule mining showed that manipulating cellphones predominantly occurred at intersections, while talking was more common on road segments. In-vehicle video analysis suggested that emotional valence varied significantly before, during, and after cellphone calls and texting. The study also noted that Louisiana’s crash database lacks detailed distraction-related information, highlighting issues with reporting quality. The significance of this research lies in its comprehensive approach to identifying risk factors and behavioral patterns associated with distracted driving in Louisiana. The findings suggest that physical countermeasures should specifically target the prevention of lane departure crashes. Furthermore, the study recommends strict enforcement of texting bans combined with awareness campaigns to mitigate distracted driving. By linking specific roadway conditions and driver demographics to crash severity, the results provide actionable insights for law enforcement and transportation planners aiming to improve road safety and reduce fatalities.
Key finding
Random forest algorithms outperformed multinomial logistic regression in predicting distracted driving crash severity, and association rule mining showed that phone manipulation primarily occurred at intersections while talking was associated with road segments.
Methodology
mixed_methods
Sample size: 60000
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- distraction detection algorithms
- visual
- external distraction
- mobile phones
- distraction laws
- incidence prevalence
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: observational prevalence, crash risk outcomes
- Theoretical Contribution: conceptual framework