Text analysis in incident duration prediction



Due to their heterogeneous case-by-case nature, plenty of relevant information about traffic incidents is communicated in free flow text fields instead of constrained value fields. As a result, such text components enclose considerable richness that is invaluable for incident analysis, modeling and prediction. However, the difficulty to formally interpret such data has led to minimal consideration in previous work.
This paper proposes the use of topic modeling, a text analysis technique, in the problem of incident duration prediction. We analyze a dataset of 2 years of accident cases and develop a duration prediction model that considers both textual and non-textual features. To demonstrate the value of the approach, we compare predictions with and without text analysis using several different prediction models.


Incident duration prediction, text analysis, topic modeling, regression models


Machine learning


Transportation Research Part C, Elsevier, November 2013

PDF File


Cited by

Year 2016 : 2 citations

 AJP Tixier, MR Hallowell, B Rajagopalanâ?¦, Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports, Automation in …, 2016

 L Jin, S Amin, Analysis of a Stochastic Switched Model of Freeway Traffic Incidents, arXiv preprint arXiv:1601.00204, 2016

Year 2015 : 8 citations

 H Park, A Haghani, Real-time prediction of secondary incident occurrences using vehicle probe data, Transportation Research Part C: Emerging …, 2015

 L Tanguy, N Tulechki, A Urieli, E Hermannâ?¦, Natural language processing for aviation safety reports: from classification to interactive analysis, Computers in Industry, 2015

 DPK Seedah, F Leite, Information Extraction for Freight-Related Natural Language Queries, Computing in Civil Engineering 2015, 2015

 Y Lu, FC Pereira, R Seshadriâ?¦, DynaMIT2. 0: Architecture Design and Preliminary Results on Real-Time Data Fusion for Traffic Prediction and Crisis Management, … (ITSC), 2015 IEEE …, 2015

 J Weng, Y Zheng, X Qu, X Yan, Development of a maximum likelihood regression tree-based model for predicting subway incident delay, Transportation Research Part C: Emerging …, 2015


 A Kurkcu, EF Morgul, K Ozbay, Extended Implementation Method for Virtual Sensors: Web-Based Real-Time Transportation Data Collection and Analysis for Incident Management, … Research Record: Journal …, 2015

 A Kurkcu, K Ozbay, Extended Implementation Method for Virtual Sensors, Publication/NA, 2015

Year 2014 : 3 citations

 R Li, Traffic incident duration analysis and prediction models based on the survival analysis approach, Intelligent Transport Systems, IET, 2014

 DPK Seedah, Retrieving information from heterogeneous freight data sources to answer natural language queries, Publication/NA, 2014

 Y He, S Blandin, L Wynterâ?¦, Analysis and real-time prediction of local incident impact on transportation networks, Data Mining Workshop ( …, 2014