Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports
Wrong-way driving (WWD) has been a long-lasting issue for transportation agencies and law enforcement, since it causes pivotal threats to road users. Notwithstanding being rare, crashes occurring due to WWD are more severe than other types of crashes. In order to analyze WWD crashes, there is a need...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-12-01
|
| Series: | International Journal of Transportation Science and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2046043022001022 |
| _version_ | 1827765224331018240 |
|---|---|
| author | Parisa Hosseini Seyedalireza Khoshsirat Mohammad Jalayer Subasish Das Huaguo Zhou |
| author_facet | Parisa Hosseini Seyedalireza Khoshsirat Mohammad Jalayer Subasish Das Huaguo Zhou |
| author_sort | Parisa Hosseini |
| collection | DOAJ |
| description | Wrong-way driving (WWD) has been a long-lasting issue for transportation agencies and law enforcement, since it causes pivotal threats to road users. Notwithstanding being rare, crashes occurring due to WWD are more severe than other types of crashes. In order to analyze WWD crashes, there is a need to obtain WWD incidents or crash data. However, it is time-consuming to identify actual WWD crashes from potential WWD crashes in large crash databases. It often involves large man-hours to review hardcopy of crash narratives in the police reports. Otherwise, it may cause an overestimation or underestimation of WWD crash frequencies. To fill this gap, the present study, as the first-of-its-kind, aims at identifying actual WWD crashes from potential WWD crashes in police reports by using machine learning methods. Recently, Bidirectional Encoder Representations from Transformers (BERT) models have shown promising results in natural language processing. In this study, we implemented the BERT model as well as five conventional classification algorithms, including Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Single Layer Perceptron (SLP) to classify crash report narratives as actual WWD and non-WWD crashes. Cross-validation and different performance metrics were used to evaluate the performance of each classification algorithm. Results indicated that the BERT model outperformed in identifying actual WWD crashes in comparison with other algorithms with an accuracy of 81.59%. The BERT classification algorithm can be implemented to reduce the time needed to identify actual WWD crashes from crash report narratives. |
| first_indexed | 2024-03-11T11:16:05Z |
| format | Article |
| id | doaj.art-fd9d007b12ac432b9c3f629d59337adf |
| institution | Directory Open Access Journal |
| issn | 2046-0430 |
| language | English |
| last_indexed | 2024-03-11T11:16:05Z |
| publishDate | 2023-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | International Journal of Transportation Science and Technology |
| spelling | doaj.art-fd9d007b12ac432b9c3f629d59337adf2023-11-11T04:27:58ZengKeAi Communications Co., Ltd.International Journal of Transportation Science and Technology2046-04302023-12-0112410381051Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reportsParisa Hosseini0Seyedalireza Khoshsirat1Mohammad Jalayer2Subasish Das3Huaguo Zhou4Department of Civil and Environmental Engineering, Center for Research and Education in Advanced Transportation Engineering Systems (CREATEs), Rowan University, 201 Mullica Hill Road, Glassboro, NJ 08028, USADepartment of Computer & Information Sciences, University of Delaware, 18 Amstel Ave, Newark, DE 19716, USADepartment of Civil and Environmental Engineering, Center for Research and Education in Advanced Transportation Engineering Systems (CREATEs), Rowan University, 201 Mullica Hill Road, Glassboro, NJ 08028, USA; Corresponding author.Civil Engineering Program, Ingram School of Engineering, Texas State University, RFM 5202, 601 University Drive, San Marcos, TX 78666, USA224 Harbert Center, Department of Civil and Environmental Engineering, Auburn University, Auburn, AL 36849, USAWrong-way driving (WWD) has been a long-lasting issue for transportation agencies and law enforcement, since it causes pivotal threats to road users. Notwithstanding being rare, crashes occurring due to WWD are more severe than other types of crashes. In order to analyze WWD crashes, there is a need to obtain WWD incidents or crash data. However, it is time-consuming to identify actual WWD crashes from potential WWD crashes in large crash databases. It often involves large man-hours to review hardcopy of crash narratives in the police reports. Otherwise, it may cause an overestimation or underestimation of WWD crash frequencies. To fill this gap, the present study, as the first-of-its-kind, aims at identifying actual WWD crashes from potential WWD crashes in police reports by using machine learning methods. Recently, Bidirectional Encoder Representations from Transformers (BERT) models have shown promising results in natural language processing. In this study, we implemented the BERT model as well as five conventional classification algorithms, including Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Single Layer Perceptron (SLP) to classify crash report narratives as actual WWD and non-WWD crashes. Cross-validation and different performance metrics were used to evaluate the performance of each classification algorithm. Results indicated that the BERT model outperformed in identifying actual WWD crashes in comparison with other algorithms with an accuracy of 81.59%. The BERT classification algorithm can be implemented to reduce the time needed to identify actual WWD crashes from crash report narratives.http://www.sciencedirect.com/science/article/pii/S2046043022001022Wrong-Way Driving CrashesCrash Report NarrativesText MiningText Classification |
| spellingShingle | Parisa Hosseini Seyedalireza Khoshsirat Mohammad Jalayer Subasish Das Huaguo Zhou Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports International Journal of Transportation Science and Technology Wrong-Way Driving Crashes Crash Report Narratives Text Mining Text Classification |
| title | Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports |
| title_full | Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports |
| title_fullStr | Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports |
| title_full_unstemmed | Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports |
| title_short | Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports |
| title_sort | application of text mining techniques to identify actual wrong way driving wwd crashes in police reports |
| topic | Wrong-Way Driving Crashes Crash Report Narratives Text Mining Text Classification |
| url | http://www.sciencedirect.com/science/article/pii/S2046043022001022 |
| work_keys_str_mv | AT parisahosseini applicationoftextminingtechniquestoidentifyactualwrongwaydrivingwwdcrashesinpolicereports AT seyedalirezakhoshsirat applicationoftextminingtechniquestoidentifyactualwrongwaydrivingwwdcrashesinpolicereports AT mohammadjalayer applicationoftextminingtechniquestoidentifyactualwrongwaydrivingwwdcrashesinpolicereports AT subasishdas applicationoftextminingtechniquestoidentifyactualwrongwaydrivingwwdcrashesinpolicereports AT huaguozhou applicationoftextminingtechniquestoidentifyactualwrongwaydrivingwwdcrashesinpolicereports |