Book chapter
Predicting Vehicle Recalls with User-Generated Contents: A Text Mining Approach
Intelligence and Security Informatics, pp.41-50
Lecture Notes in Computer Science, Springer International Publishing
2015
DOI: 10.1007/978-3-319-18455-5_3
Abstract
Vehicle safety issues and component defects result in property losses and fatalities. Our study proposes a new method to predict vehicle recalls based on user generated contents in online discussion forums. Vehicle defects can cause bodily injuries and sometimes deadly consequences. However, vehicle recalls will not be issued until damage has occurred. Online vehicle discussion forums usually contain traits of vehicle defects long before manufacturers and government agencies take investigative actions. We find overlapping components in user generated contents and official recall notices. Our proposed recall prediction method can correctly predict vehicle recalls once in every two recall events. It is our hope that our proposed technique can be used to monitor online vehicle discussion forums and prompt the manufacturers and government agencies to issue recalls before catastrophic accidents occur. Our research has significant practical implications to vehicle and transportation safety.
Details
- Title: Subtitle
- Predicting Vehicle Recalls with User-Generated Contents: A Text Mining Approach
- Creators
- Xuan Zhang - Department of Computer Science, College of Engineering, Virginia Tech, Blacksburg, USAShuo Niu - Department of Computer Science, College of Engineering, Virginia Tech, Blacksburg, USADa Zhang - Department of Computer Science, College of Engineering, Virginia Tech, Blacksburg, USAG. Alan Wang - Department of Business Information Technology, Pamplin College of Business, Virginia Tech, Blacksburg, USAWeiguo Fan - Department of Accounting and Information Systems, Pamplin College of Business, Virginia Tech, Blacksburg, USA
- Resource Type
- Book chapter
- Publication Details
- Intelligence and Security Informatics, pp.41-50
- Publisher
- Springer International Publishing; Cham
- Series
- Lecture Notes in Computer Science
- DOI
- 10.1007/978-3-319-18455-5_3
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 2015
- Academic Unit
- Business Analytics
- Record Identifier
- 9984083225602771
Metrics
14 Record Views