Modeling anger and aggressive driving behavior in a dynamic choice-latent variable model

Influence of emotions on the aggressive driving behavior of online -car-hailing drivers based on association rule mining

Emotion is an important factor that can lead to the occurrence of aggressive driving. This paper proposes an association rule mining-based method for analysing contributing factors associated with aggressive driving behaviour among online car-hailing drivers. We collected drivers' emotion data in real time in a natural driving setting. The findings show that 29 of the top 50 association rules for aggressive driving are related to emotions, revealing a strong relationship between driver emotions and aggressive driving behaviour. The emotions of anger, surprised, happy and disgusted are frequently associated with aggressive driving behaviour. Negative emotions combined with other factors (for example, driving at high speeds and high acceleration rates and with no passengers in the vehicle) are more likely to lead to aggressive driving behaviour than negative emotions alone. The results of this study provide practical implications for the supervision and training of car-hailing drivers.

Analysis of speed reductions and crash risk of aggressive drivers during emergent pre-crash scenarios at unsignalized intersections

Aggressive driver behavior (ADB) is often linked with road crashes, especially during crash imminent situations. Previous studies demonstrated that ADB was positively correlated with collision risk; however, this relationship has not quantified evidently. This study aimed to analyze drivers' collision risk and speed reduction behavior during an emergent pre-crash scenario (such as a conflict encroaching into an unsignalized intersection at different critical time gaps) using a driving simulator. The effect of ADB on crash risk is investigated using the time to collision (TTC). Further, drivers' collision evasive behavior is analyzed using speed reduction time (SRT) survival probabilities. Fifty-eight Indian drivers are identified as aggressive, moderately aggressive, and, non-aggressive based on aggressive indicators such as vehicle kinematics (percentage of the time spent in speeding and rapid accelerations, maximum brake pressure, etc.). Two separate models are built to analyze ADB effects on TTC and SRT using a Generalized Linear Mixed Model (GLMM) and a Weibull Accelerated Failure Time (AFT) model, respectively. From the results, it can be observed that aggressive drivers' TTC and SRT are reduced by 82% and 38%, respectively. Compared to a 7 sec conflict approaching time gap, TTC is reduced by 18%, 39%, 51%, and 58% for 6 sec, 5 sec, 4 sec, and 3 sec conflict approaching time gaps, respectively. The estimated SRT survival probabilities for aggressive, moderately aggressive and non-aggressive drivers are 0%, 3% and 68% at 3 sec of conflict approaching time gap, respectively. SRT survival probability increased by 25% for matured drivers and decreased by 48% for drivers who tend to engage in frequent speeding. Important implications of the study findings are discussed.

Analysis of driver characteristics, self-reported psychology measures and driving performance measures associated with aggressive driving

Whereas aggressive driving mainly causes speed-related crashes, aggressive driving may be reduced to improve road safety by identifying aggressive driving behaviour, aggressive drivers' characteristics, and their underlying motivational and psychological processes. Previous studies show that both driving performance and self-reported measures of aggressive driving are effective means to identify aggressive drivers. However, these studies assessed aggressive driving patterns across only a limited number of events, did not relate driver characteristics to aggressive driving in each event, and used chiefly vehicle kinematics variables (e.g., mean speed), but not vehicle dynamics variables (e.g., brake pedal force) which better capture driver reaction and decision-making. To address these limitations, this study assessed driver characteristics, self-reported psychological measures, and driving performance measures associated with aggressive driving among 55 drivers' behaviours in 9driving events using a driving simulator and survey responses. The results of structural equation models showed that unique aggressive driving patterns and driver characteristics related to aggressive driving vary among different driving events. As such, we recommend road safety policies to reduce aggressive driving based on the findings in this study.

Trait anger causes risky driving behavior by influencing executive function and hazard cognition

Drivers with a high level of trait anger feel more intensity of anger on road, contributing to more risky driving behavior and further increasing the probability of collisions. It seems that trait anger directly correlates with risky driving behavior, but how it works in detail remains unknown and previous research indicated executive function and hazard cognition may play a mediation role in it. Our research aims to explore the relationship among these variables and test if there is a multiple mediation model. We sampled 302 valid participants and used online questionnaires, containing trait anger scale (TAS), executive function index (EFI), hazard cognition scale (HCS; representing attitudes towards risky driving behavior), driver behavior questionnaire (DBQ), and self-reported traffic violations (e.g., accidents, penalty points, fines). Hierarchical multiple linear regression of DBQ results show trait anger is a medium but statistically significant predictor of risky driving behavior and drivers' attitude towards risky situations can significantly predict risky driving behavior at medium effect. But risky driving behavior cannot be predicted by executive function. Interestingly, opposing to prior research, zero-inflated Poisson regression analysis of self-reported traffic violations suggests trait anger negatively predicts accidents and fines in the zero-inflation model, and hazard cognition negatively predicts penalty points. Notably, the executive function negatively predicts penalty points and fines in the count model, which confirms our hypothetical direction. They all represent a small effect size in this nonlinear regression model. Path analysis suggested that trait anger influences risky driving behavior through executive function, and hazard cognition both separately and jointly. This study provides a theoretical framework for the transaction model of aggressive driving behavior and offers some possible interventions toward the effect of trait anger on risky driving behavior.

A Comprehensive Review of Driving Style Evaluation Approaches and Product Designs Applied to Vehicle Usage-Based Insurance

Vehicle insurance is a very important source of income for insurance companies, and it is closely related to the driving style performed by driving behavior. Different driving styles can better reflect the driving risk than the number of violations, claims, and other static statistic data. Subdivide the vehicle insurance market according to the personal characteristics and driving habits of the insured vehicles, and studying the personalized vehicle insurance products, will help the insurance companies to improve their income, help the drivers to change their bad driving habits, and thus help to realize the healthy development of the vehicle insurance industry. In the past 20 to 30 years, more and more insurance companies around the world have launched vehicle usage-based insurance (UBI) products based on driving style analysis. However, up to now, there are few comprehensive reports on commercial vehicle UBI products and their core driving risk assessment methods. On the basis of literature indexing on the Web of Science and other academic platforms by using the keywords involved in vehicle UBI, over 100 relevant works of literature were screened in this paper, and a detailed and comprehensive discussion on the driving style evaluation methods and the design of commercial vehicle UBI products during the past 20 to 30 years has been made, hoping to get a full understanding of the possible factors affecting driving style and the collectible data that can reflect these factors, and to get a full grasp of the developing status, challenges and future trends in vehicle insurance branch of the Internet of Vehicles (IoV) industry.

A Double-Layered Belief Rule Base Model for Driving Anger Detection Using Human, Vehicle, and Environment Characteristics: A Naturalistic Experimental Study

"Road rage," namely, driving anger, has been becoming increasingly common in auto era. As "road rage" has serious negative impact on road safety, it has attracted great concern to relevant scholar, practitioner, and governor. This study aims to propose a model to effectively and efficiently detect driving anger states with different intensities for taking targeted intervening measures in intelligent connected vehicles. Forty-two private car drivers were enrolled to conduct naturalistic experiments on a predetermined and busy route in Wuhan, China, where drivers' anger can be induced by various incentive events like weaving/cutting in line, jaywalking, and traffic congestion. Then, a data-driven model based on double-layered belief rule base is proposed according to the accumulation of the naturalistic experiments data. The proposed model can be used to effectively detect different driving anger states as a function of driver characteristics, vehicle motion, and driving environments. The study results indicate that average accuracy of the proposed model is 82.52% for all four-intensity driving anger states (none, low, medium, and high), which is 1.15%, 1.52%, 3.53%, 5.75%, and 7.42%, higher than C4.5, BPNN, NBC, SVM, and kNN, respectively. Moreover, the runtime ratio of the proposed model is superior to that of those models except for C4.5. Hence, the proposed model can be implemented in connected intelligent vehicle for detecting driving anger states in real time.

A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning

Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F₁-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.

Dimensions of driving-related emotions and behaviors: An exploratory factor analysis of common self-report measures

OBJECTIVE

A wide variety of driving self-report measures are purported to assess drivers' behaviors and emotions. However, little is known about the underlying factor structure of these measures. This study examined the factor structure of several self-report measures frequently utilized in the assessment of driving-related behaviors and emotions.

DESIGN

Cohort survey in a large sample (n = 287) of young adults (mean age = 19.91 years, SD = 1.65).

RESULTS

Exploratory factor analysis revealed a four-factor structure that included reckless driving behaviors, negative driving-related emotions, aggressive driving behaviors in response to perceived transgressions from other drivers, and perceived aggressive driving behaviors from other drivers. Aggressive driving behaviors not performed in response to other drivers loaded onto both aggressive driving-related factors.

CONCLUSIONS

The factor structure derived in the present study suggests considerable overlap in the content across commonly administered driving self-reports, while also suggesting four distinct dimensions of self-reported driving emotions and behaviors. Whereas some of these dimensions have been explored considerably in the literature (e.g., negative emotions), others deserve further exploration (e.g., perceived aggressive driving behaviors from other drivers). Implications for clinical practice and future investigations are discussed.

Effects of congestion on drivers' speed choice: Assessing the mediating role of state aggressiveness based on taxi floating car data

Inappropriate cruising speed, such as speeding, is one of the major contributors to the road safety, which increases both the quantitative number and severity of traffic accidents. Previous studies have indicated that traffic congestion is one of the primary causes of drivers' frustration and aggression, which may lead to inappropriate speed choice. In this study, the large taxi floating car data (FCD) was used to empirically evaluate how traffic congestion-related negative moods, defined as state aggressiveness, affected drivers' speed choice. The indirect effect of traffic delay on the cruising speed adjustment through the state aggressiveness was assessed through the mediation analysis. Furthermore, the moderated mediation analysis was performed to explore the effect of driver type, value of time, and working duration on the mediation role of state aggressiveness. The results proved that the state aggressiveness was the mediator of the relationship between travel delays and driving speed adjustment, and the mediation role was different across various driver types. As compared to the aggressive drivers, the normal drivers and the steady drivers tended to behave more aggressively after experiencing non-recurrent congestion during the early stage of the trips. When the value of time was high, steady drivers were more likely to adjust their speed choice although the effect was not statistically significant for other driver types. The validation results indicated that the speed model incorporating state aggressiveness could better predict the travel time than the traditional speed model that only considering the specific expected speed distribution. The prediction results for the manifest indicators of state aggressiveness, such as the maximum speed and the speed deviation, also demonstrated a reasonable reflection of the field data.

The incremental validity of the dark triad in predicting driving aggression

This research tested the association between the Dark Triad and driving aggression as well as the incremental validity of the Dark Triad in predicting aggressive driving and the mediation role of the Dark Triad in the relationship between Big Five personality factors and aggressive driving. 274 undergraduate students in Study 1 and 95 amateur drivers in Study 2 completed measures of the Dark Triad (Machiavellianism, Narcissism and Psychopathy), the Big Five personality factors and the aggressive driving expression. Results showed that all the Dark Triad traits were related to aggressive driving behavior in both Study 1 and Study 2 and that the Dark Triad predicted driving aggression after the effect of the Big five personality factors was controlled, with Psychopathy being the strongest predictor of driving aggression in both Study 1 and Study 2. Machiavellianism and Psychopathy mediated the relationship between Emotional Stability, Agreeableness, Conscientiousness on one hand and aggressive driving on the other hand.