Name
Abstract | ||
|---|---|---|
Conventional approaches to road hazard detection involve manual inspections of roads by government transportation agencies. These approaches are usually expensive to execute, and sometimes are not able to capture the most recent hazards. Moreover, they often only focus on major highways due to a lack of sufficient manpower. Consequently, many hazards on minor roads get ignored, which may pose serious dangers to drivers. In this paper, we demonstrate an application of Twitter to atomically determining road hazards. By building language models based on Twitter users' online communication, our system aims at pinpointing potential road hazards that pose driving risks. The likelihood of poor driving conditions can then be exposed via map overlays to warn drivers about potentially dangerous driving conditions in their locale or on current routes, thereby significantly reducing the chances of an accident occurring. To the best of our knowledge, this is the first work demonstrating the utility of social media to automatically detect road hazards. We conduct experiments on a testbed of tweets discussing road conditions and the initial results demonstrate the effectiveness of our approach. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1145/2600428.2609550 | SIGIR |
Keywords | Field | DocType |
language models,road hazards,content analysis and indexing,twitter,sentiment analysis | Dangerous driving,Social media,Sentiment analysis,Computer science,Computer security,Testbed,Language model,Government | Conference |
Citations | PageRank | References |
4 | 0.48 | 6 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Avinash Kumar | 1 | 4 | 0.48 |
| Miao Jiang | 2 | 12 | 1.66 |
| Yi Fang | 3 | 379 | 32.01 |