The Effect of Road Rage Mood Changes on Driving Safety and

Intelligent Regulation Strategies

Jiaxi Li

, Shuo Li

and Peixuan Zuo

3,*

GCTB-NSU Joint Institute of Technology, Guangzhou College of Technology and Business, Foshan, China

School of Computer Science and Mathematics, Anyang University, Shangqiu, China

College of Computer and Information Engineering, Tianjin Chengjian University, Tianjin, China

Keywords: Road Rage, Intelligent Regulation, Questionnaire Survey, Influencing Factor.

Abstract: With the continuous growth in the global number of motor vehicles, traffic safety has become a critical

concern for policymakers, urban planners, and individuals alike. Through questionnaire survey, the

characteristics involve various factors such as living environment and personal habits are collected. The

findings underscore the necessity of targeted interventions to enhance road safety. Key measures include route

optimization to reduce financial strain on commercial drivers, mindfulness-based programs to mitigate

distraction from family-related stress, and congestion alert systems supported by intelligent transport

infrastructure. Integrating stress management into driver training also contributes to lowering the risk of

incidents associated with emotional or cognitive overload. To support effective implementation, lightweight

computational models—such as pruned neural networks or decision tree ensembles—are recommended for

their balance of predictive performance and computational efficiency. A hybrid cloud-edge architecture is

further proposed to optimize real-time processing: latency-sensitive tasks are handled locally, while

computationally intensive operations are offloaded to the cloud. This strategy enables the deployment of

advanced safety functions without requiring substantial hardware investment, making it suitable for settings

with limited technical resources.

1 INTRODUCTION

Road rage, conceptualized as aggressive driving

behavior provoked by anger or frustration, has

become a prominent issue in the realm of global

traffic safety. With the continuous increase in motor

vehicle ownership, there has been a concomitant rise

in traffic incidents linked to emotional dysregulation,

particularly manifestations of road rage. Empirical

research has established that anger impairs drivers’

cognitive functioning, notably prolonging reaction

times by approximately 15–20%, while

simultaneously heightening the likelihood of

engaging in high-risk maneuvers such as excessive

speeding, abrupt lane changes, and tailgating. These

behaviors significantly amplify the risk of traffic

collisions (Ren et al., 2021). The antecedents of road

rage are multifactorial. Acute situational stressors—

such as traffic congestion, adverse road and weather

conditions, and provocative driving actions (e.g.,

sudden merging or queue-jumping)—interact with

chronic psychological stressors, including

occupational demands and familial pressures, to

intensify emotional reactivity in driving contexts

(Chai et al., 2022). Given its considerable prevalence

and complex etiological underpinnings, the

prevention and management of road rage are critical

to advancing traffic safety and curbing the incidence

of emotionally driven vehicular incidents

(Subramanian & Bhargavi, 2024).

Recent advancements in intelligent transportation

systems and behavioral monitoring technologies have

opened new avenues for the early identification and

mitigation of emotionally induced driving risks. Ren

et al. undertook a systematic investigation into both

intrinsic and extrinsic determinants of road rage (Ren

et al., 2021), identifying physiological markers—

such as elevated cortisol levels—and environmental

variables, including urban traffic density, as salient

predictors of aggressive driving behavior. These

insights underscore the necessity of integrating

psychological theoretical frameworks with

technological interventions to address the

multifaceted nature of road rage. In a related line of

Li, J., Li, S. and Zuo, P.

The Effect of Road Rage Mood Changes on Driving Safety and Intelligent Regulation Strategies.

DOI: 10.5220/0014320600004718

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 2nd International Conference on Engineering Management, Information Technology and Intelligence (EMITI 2025), pages 71-78

ISBN: 978-989-758-792-4

research, Li et al. developed a multimodal emotion

recognition system that integrates enhanced Mel-

frequency cepstral coefficient (MFCC) features (Li et

al., 2022), a firefly algorithm-optimized probabilistic

neural network, and advanced pattern recognition

techniques. This system facilitates real-time

monitoring of drivers’ emotional states, thereby

offering a technologically driven approach for

proactive risk detection and management in traffic

settings.

The proposed FA-PNN model uses voice signals

and achieves a recognition accuracy of 93.0% for

detecting road rage episodes (Li et al., 2022). Key

challenges include ensuring system robustness under

dynamic driving conditions. Real-time processing

demands present additional technical barriers. Ethical

concerns about data security and individual privacy

also require attention. This study investigates how

road rage affects driving safety through physiological

responses, cognitive impairments, and behavioral

deviations. Multimodal data such as facial

expressions, vocal cues, and heart rate are used to

build a dynamic emotion–behavior mapping

framework. This framework helps identify critical

points when emotional escalation leads to high-risk

driving behaviors. Based on the analysis, the study

proposes adaptive in-vehicle regulation strategies.

Personalized auditory feedback and responsive

control interfaces are designed to mitigate driver

anger in real time. Insights from psychology, traffic

safety engineering, and intelligent system design

support the development of an emotion-sensitive

vehicle safety approach. This work improves emotion

recognition accuracy and strengthens human–

machine interaction under changing driving

conditions. It also provides evidence-based

recommendations for system design and regulation to

reduce road rage incidents. The study enhances

theoretical understanding and offers practical

solutions for intelligent emotional regulation,

contributing to safer traffic systems.

2 RESEARCH SKETCH

2.1 Background and Importance of the

Study

With the continuous growth in the global number of

motor vehicles, traffic safety issues have increasingly

garnered attention.

Among the many factors influencing traffic

safety, drivers' emotional states have become

recognized as important contributors to traffic

accidents. Episodes of road rage are especially linked

to elevated accident risk. Empirical studies show that

anger significantly disrupts core cognitive functions.

These functions include attentional control, risk

evaluation, and decision-making. Cognitive

impairments caused by anger increase the likelihood

of high-risk driving behaviors. Examples of such

behaviors are excessive speeding, abrupt lane

changes, and tailgating (Ren et al., 2021). These risky

behaviors threaten not only the safety of the initiating

driver but also affect surrounding drivers. Reactive

behaviors triggered in nearby drivers can lead to

cascading effects on the road. Such chain reactions

amplify the risk of multi-vehicle collisions and severe

traffic incidents (Chai et al., 2022).

In recent years, with the rapid advancement of

artificial intelligence, vehicular networking, and

biometric monitoring technologies, intelligent

regulation strategies have shown promising

application prospects in the field of driving safety.

Utilizing multimodal data (such as driving behavior,

facial expressions, vocal characteristics, heart rate,

etc.) for emotion monitoring, combined with

personalized intervention measures, holds the

potential to effectively mitigate road rage and thus

reduce driving risks (Li et al., 2022). However,

existing intelligent regulation technologies still face

numerous challenges in terms of emotion recognition

accuracy, real-time performance, and privacy

protection. Therefore, exploring the specific

mechanisms by which road rage affects driving safety

and investigating optimization directions for

intelligent regulation strategies are of significant

academic value and practical importance.

2.2 Objectives and Scope of the Study

2.2.1 Objectives to Uncover the Mechanisms

by Which Road Rage Affects Driving

Safety

To analyze the three-level linkage mechanism of

physiological, cognitive, and behavioral aspects of

road rage, and to quantify the dynamic impact of

emotional fluctuations on driving behavior. To

construct a mapping model of emotions and

behaviors, identifying the critical points of emotional

outbursts and the spatiotemporal characteristics of

high-risk driving behaviors. To develop a theoretical

framework for intelligent regulation technology,

designing multimodal emotion perception and

adaptive intervention strategies to achieve real-time

monitoring and dynamic regulation of road rage. To

explore human-machine collaborative regulation

EMITI 2025 - International Conference on Engineering Management, Information Technology and Intelligence

paradigms, enhancing drivers' emotional regulation

capabilities and driving safety. To promote

interdisciplinary integration and technological

application, integrating research achievements from

psychology, artificial intelligence, traffic

engineering, and other fields to build a data-driven

emotion modeling and regulation system (Li et al.,

2022).

2.2.2 Research Scope

The Intersection of Psychological Mechanisms,

Environmental Factors, and Intelligent Technology.

The research scope includes the study of the impact

mechanisms of road rage emotions, the development

and validation of intelligent regulation technologies,

the quantitative analysis of environmental and

dynamic factors, and the partial validation of

interdisciplinary integration and technological

applications. It aims to provide scientifically valuable

and practically significant solutions for the field of

traffic safety.

2.2.3 Research Methods

Through a questionnaire survey, the public's attitude

towards intelligent treatment of road rage and the

common characteristics of people who often suffer

from road rage are collected. The characteristics

involve various factors such as living environment

and personal habits. This research combines

psychology, artificial intelligence, and traffic

engineering to create an overall framework for

emotionally aware driving safety systems, provide

actionable strategies for policymakers, and provide

technological advancements for safer transportation

ecosystems.

3 MECHANISMS AND KEY

INFLUENCING THE IMPACT

OF ROAD RAGE ON DRIVING

SAFETY

3.1 Figures

Emotions profoundly influence driving behavior

through cognitive and physiological pathways

(StevenLove & Grégoire, 2025). Road rage,

characterized by anger and frustration, disrupts

critical neural and psychological processes required

for safe driving. Neurobiological studies reveal that

anger activates the amygdala, which suppresses

prefrontal cortex functions responsible for logical

reasoning and impulse control (Ren et al., 2021). This

imbalance leads to delayed reaction times and

impaired risk perception. For instance, drivers

experiencing road rage exhibit a 15–20% slower

response to sudden hazards compared to calm drivers,

as demonstrated in simulated driving experiments

(Chai et al., 2022).

The Cognitive Appraisal Theory further explains

how emotions shape driving decisions. Anger distorts

environmental evaluations, fostering hostile

interpretations of benign actions (e.g., perceiving a

safe lane change as intentional provocation). Such

misjudgments increase the likelihood of retaliatory

behaviors, such as tailgating or aggressive honking

(Li et al., 2022). Additionally, the Yerkes-Dodson

Law highlights the non-linear relationship between

arousal and performance. While moderate stress

enhances alertness, excessive arousal from road rage

surpasses optimal thresholds, degrading situational

awareness and decision-making accuracy.

Physiological markers, such as elevated cortisol

levels and increased heart rate, correlate with road

rage intensity. A 2022 study using wearable

biosensors found that drivers with cortisol spikes

above baseline levels were 2.3 times more likely to

engage in reckless overtaking (Chai et al., 2022).

These findings underscore the need for interventions

targeting both emotional regulation and physiological

stress responses (Subramanian & Bhargavi, 2023).

3.2 Empirical Study of Emotionally

Induced Driving Risk

Empirical evidence solidifies the link between road

rage and accident risks. Analysis of traffic incident

databases reveals that 28–35% of collisions involve

drivers exhibiting overt anger, with aggressive

maneuvers (e.g., abrupt lane changes) accounting for

60% of these cases (Ren et al., 2021). A notable

example includes a 2021 multi-vehicle collision in

Beijing, where post-accident interviews confirmed

that the initiating driver had been provoked by

prolonged traffic congestion, leading to reckless

speeding (Chai et al., 2022).

Individual differences modulate emotional

impacts. Experienced drivers demonstrate resilience

through adaptive coping strategies, such as mindful

breathing or adjusting driving routes. In contrast,

novices with limited stress management skills are

50% more prone to road rage escalation (Li et al.,

2022). Personality traits also play a role: neurotic

individuals report higher anger persistence, while

The Effect of Road Rage Mood Changes on Driving Safety and Intelligent Regulation Strategies

conscientious drivers employ preemptive measures

like avoiding peak-hour traffic (Smith & Doe, 2023).

Technological advancements offer empirical

insights. For example, in-vehicle cameras and AI

algorithms analyzing facial expressions achieved

89% accuracy in detecting anger episodes during a

2023 field trial, enabling real-time warnings to

mitigate risks (Global, 2023).

3.3 Environmental and Dynamic

Factors

Environmental stressors exacerbate road rage and its

consequences. Urban settings with dense traffic and

frequent interruptions (e.g., pedestrian crossings)

heighten cognitive load, doubling frustration levels

compared to rural driving (National Traffic Safety

Administration, 2021). A 2022 study simulating rush-

hour conditions found that drivers exposed to honking

and abrupt braking exhibited a 45% increase in

aggressive acceleration patterns (Smith & Doe,

2023).

Dynamic factors, such as temporal mood

fluctuations, further complicate risk profiles.

Persistent anger, often stemming from pre-existing

stress, correlates with chronic cortisol elevation,

impairing long-term vigilance. Intermittent rage,

triggered by immediate provocations (e.g., cut-offs),

results in impulsive actions like unsafe overtaking.

Wearable sensor data from a 2023 cohort study

showed that drivers with persistent anger had 30%

higher near-miss incident rates than those with

intermittent episodes (Global, 2023).

Mitigation strategies include intelligent

transportation systems (ITS) that adapt to

environmental stressors. For instance, adaptive cruise

control reduces tailgating tendencies, while real-time

traffic rerouting minimizes congestion-induced

frustration. Pilot programs integrating emotion-aware

AI in vehicles reduced road rage incidents by 22%

through personalized interventions (e.g., calming

music or voice prompts) (Global, 2023).

4 THE IMPACT OF LIFE STRESS

ON ROAD RAGE

This chapter analyzes how life stress influences road

rage behaviors based on a survey of 204 drivers

(predominantly males aged 25–35). Key findings

include:

4.1 Stress Distribution

As shown in Table 1, 44.12% reported moderate

stress, and 25.49% severe stress. Family pressure

(67.16%) and economic burdens (36.27%) were

primary stressors (Questions 5–6).

Table 1: Dominant Stressors and Their Demographic

Correlates.

Family pressure as the main source of stress

subtotal percentage

Work pressure 88 43.14%

Family pressure 137 67.16%

Economic

pressure

74 36.27%

Social pressure 104 50.98%

4.2 Behavioral Correlations

As shown in Table 2 and 3, drivers with

moderate/severe stress showed higher rates of traffic

signal violations (73.53%) and aggressive lane

changes (50%) (Question 7). Severe stress correlated

with intentional blocking (25.49%) and distracted

driving (35.78%) (Question 10).

Table 2: Driving issues induced by moderate levels of

stress.

Moderate stress level group

subtotal percentage

Overspeed driving for saving time 22 24.44%

Frequent lane changes and

overtaking

47 52.22%

Ignore the traffic lights 65 72.22%

Distracted driving 33 36.67%

Table 3: Driving issues induced by severe levels of stress

Severe stress level group

subtotal percentage

Overspeed driving for saving time 15 28.85%

Frequent lane changes and

overtaking

22 42.31%

Ignore the traffic lights 42 80.77%

Distracted driving 17 32.69%

EMITI 2025 - International Conference on Engineering Management, Information Technology and Intelligence

4.3 Stress-Specific Effects

As shown in Table 4, based on a questionnaire survey

of 204 drivers (predominantly male aged 25–35

years), this section examines the persistent impact of

chronic stressors on driving emotions and behaviors.

The findings indicate that long-term factors,

including family-related stress, financial strain, and

occupational pressure, significantly elevate driving

risks through cumulative effects (Questions 5–6 and

10).

Table 4: Dynamic Impact of Chronic Stressors on Driving

Behavior: A Longitudinal Analysis.

Driving behavior caused by stress

subtotal percentage

Work pressure

34 16.67%

Family pressure

99 48.53%

Economic pressure

90 44.12%

Social pressure 66 32.35%

The traffic rules are unreasonable 34 16.67%

Personality factors 34 16.67%

4.4 Coping Strategies

As shown in Table 5, Active interventions (e.g.,

slowing down: 57.84%) outperformed passive

methods (e.g., music: 36.27%), yet 24.02% used no

strategies (Question 11).

Table 5: Adopted Coping Strategies for Stress-Induced

Road Rage.

Listen to music/podcasts 54 39.42%

Take a deep breath or meditate 58 42.34%

Talk with the passengers 79 57.66%

Deliberately reduce the vehicle speed 75 54.74%

No mitigation method 35 25.55%

4.5 Mechanisms

As shown in Table 6 and 7, Chronic stress elevates

cortisol, impairing decision-making, while hostile

attribution bias (26.96%) escalates rage.

Environmental triggers (e.g., congestion: 31.37%)

worsen stress-behavior cycles (Questions 10, 12).

Table 6: Psychological Factors and Traffic Scenarios

Associated with Driving Behavior.

Psychological factors influencing driving behavior

subtotal percentage

Driving comparison behavior 14 26.92%

Personality factors 17 32.69%

distraction due to high pressure 15 28.85%

Road rage occurs due to stress 14 26.92%

Table 7: Traffic Scenarios as Triggers for Stress-Related

Driving Behaviors

Traffic scenes encountered in the past month

subtotal percentage

The road condition is not good 10 19.23%

The weather is bad 10 19.23%

There are obstacles on the road but

no warning signs are placed

11 21.15%

The transportation infrastructure is

unreasonable

21 40.38%

The vehicle in front changes lanes

or make U-turns at will

9 17.31%

Be disturbed by the high beams of

oncoming vehicles at night

10 19.23%

The speed of the vehicle in front is

too slow

9 17.31%

The vehicles behind frequently

flash their lights or honk to urge

them on

6 11.54%

Other vehicles cut in line and cut in 21 40.38%

Non-motorized vehicles or

pedestrians do not abide by traffic

rules

7 13.46%

The vehicle in front failed to start in

time when the green light was on

11 21.15%

There has been a long period of

road congestion

18 34.62%

The influence of other people in the

vehicle

4 7.69%

Forced lane changes due to being in

a hurry

19 36.54%

Frequently check the navigation

time due to anxiety

10 19.23%

Cut off the car maliciously out of

anger

5 9.62%

The Effect of Road Rage Mood Changes on Driving Safety and Intelligent Regulation Strategies

Implications: Tailored interventions are critical—

route optimization for economic stress, meditation

prompts for family stress, and congestion alerts via

intelligent systems. Integrating stress management

into driver training can enhance safety.

5 CURRENT CHALLENGES AND

FUTURE DIRECTIONS

5.1 Technical Limitations

Existing road rage detection technologies such as

voice analysis and facial recognition face substantial

limitations under real-world driving conditions.

Environmental interferences often compromise

system accuracy. These interferences include

windshield glare, facial coverings like masks, and

ambient noise from music or in-cabin conversations

(Li et al., 2022). Vehicle onboard computational units

frequently operate under limited processing capacity.

This constraint reduces the system’s ability to

respond quickly during safety-critical events.

Scenarios requiring immediate action, such as

emergency braking or rapid hazard avoidance,

highlight the urgency of addressing these limitations.

This study proposes computationally efficient

solutions to overcome current challenges. It

introduces lightweight neural architectures that

support fast processing under resource constraints. It

also develops hybrid cloud–edge computing

frameworks that distribute the computational load

effectively. These approaches improve real-time

emotional monitoring and reduce the need for high-

performance hardware. They further enable the

scalable deployment of emotion-aware driving

systems across a wide range of vehicles (Li et al.,

2022).

5.2 Ethical and Privacy Concerns

The collection and use of biometric indicators such as

heart rate, facial expressions, and vocal features raise

serious ethical and privacy concerns in emotion-

aware driving systems (Subramanian & Bhargavi,

2023). Drivers express particular concern about the

potential misuse of their data. Risks include insurance

premium adjustments based on inferred stress levels

and unauthorized access that could lead to data

breaches and exploitation. Overly intrusive

interventions may further reduce user acceptance. For

example, emotion-triggered speed restrictions can

provoke resistance and weaken trust in intelligent

vehicle technologies. Addressing these concerns

requires the implementation of privacy-preserving

strategies. Effective solutions prioritize transparency,

user autonomy, and data security (Subramanian &

Bhargavi, 2023). Providing intuitive controls that

allow users to enable or disable monitoring functions

enhances perceptions of control and consent (Chris,

2023). Allowing users to manage data-sharing

preferences further supports this goal. Applying

rigorous anonymization methods ensures that

biometric data are stored and transmitted in de-

identified form. This approach reduces privacy risks

while maintaining system utility (Jeon, 2015).

Achieving a balance between technological efficacy

and ethical safeguards is critical. Such balance fosters

user trust and supports the sustainable adoption of

road rage mitigation technologies (Global, 2023).

5.3 Future Research Priorities

Future research should prioritize the development of

cost-effective, user-friendly tools to support drivers'

emotional self-regulation. Smartphone-based

applications delivering non-intrusive prompts—such

as “Signs of stress detected—consider taking a

break”—or subtle haptic feedback represent practical

interventions for mitigating emotional escalation

during driving (StevenLove & Grégoire, 2025).

Equally important is the advancement of human–

machine collaborative systems that emphasize

advisory rather than prescriptive functions.

Suggestions such as rest stops or alternative routes

should be communicated in ways that preserve driver

autonomy and reinforce system trust (Subramanian &

Bhargavi, 2023).

At a systemic level, long-term research efforts

must address the standardization of emotion

recognition technologies, including the creation of

unified performance metrics and evaluation protocols

to enable cross-platform comparability. Establishing

industry-wide guidelines is also essential to ensure

scalability, interoperability, and long-term

sustainability. Concurrently, interdisciplinary

collaboration among psychology, transportation

engineering, and computational modeling is critical

for refining data-driven regulatory frameworks and

promoting driver emotional well-being (DePasquale

et al., 2001). By integrating these directions, future

work can promote iterative technological refinement,

uphold ethical principles, and enhance real-world

applicability. Ultimately, this will contribute to the

formation of comprehensive and adaptive solutions

that balance safety, efficiency, and user acceptance in

EMITI 2025 - International Conference on Engineering Management, Information Technology and Intelligence

intelligent transportation systems (Subramanian &

Bhargavi, 2023).

6 CONCLUSION

Road rage is mainly triggered by anger and frustration

and poses a serious threat to driving safety by

impairing cognitive function and increasing reaction

time and aggressive behavior. Research has shown

that emotional states directly influence driver

performance through physiological changes such as

elevated cortisol levels and increased heart rate.

Driving simulator studies confirm that individuals

experiencing anger respond more slowly to sudden

hazards than those in neutral states. Long-term stress

can impair executive function and increase cognitive

biases such as hostile attribution. This bias raises the

likelihood of unsafe driving decisions. Recent

advances in intelligent regulation technologies have

supported the development of multimodal emotion

monitoring systems. These systems detect driver

states by using voice signals, facial expressions, and

physiological indicators. They can trigger real-time

interventions designed to lower emotional arousal

during driving. Examples of such interventions

include auditory cues and ambient lighting

adjustments. Field studies report up to 89% accuracy

in identifying anger episodes through in-vehicle

algorithms. Despite these achievements, current

systems continue to face technical limitations.

Challenges include reduced accuracy under

conditions of glare or ambient noise. In addition,

limited onboard hardware capacity constrains system

responsiveness in time-sensitive situations. In

addition, the use of biometric data raises concerns

about data security, informed consent, and possible

misuse. Solving the problem of road rage requires an

integrated framework that considers individual

drivers, in-vehicle systems, and external conditions to

ensure both safety and user acceptance.

Urban traffic congestion often leads to emotional

arousal during driving. Poor road design can further

increase frustration by limiting maneuverability and

visibility. Provocative driving behaviors, such as

sudden merging or queue-jumping, directly trigger

anger in many drivers. Individual factors like

personality traits, stress resilience, and emotional

regulation capacity influence how drivers respond to

these stressors. Intelligent transportation systems

should integrate adaptive functions to reduce

emotional load. Cruise control systems that adjust

following distance can help prevent tailgating.

Navigation tools that offer real-time rerouting can

reduce stress caused by delays. Preliminary studies

have shown that emotion-responsive systems can

reduce road rage incidents by up to 22 percent.

Personalized interventions such as context-sensitive

voice prompts have been especially effective in

regulating driver emotions. Future research should

focus on developing robust emotional models

grounded in interdisciplinary knowledge. Input from

psychology, traffic engineering, and computational

modeling is essential to build accurate and applicable

systems. Ethical concerns must be addressed through

clear anonymization protocols and user-controlled

monitoring settings. Cost-effective tools such as

mobile applications can improve accessibility and

promote emotional self-regulation. Standardized

human–machine interaction protocols will support

consistent user experiences across systems.

Combining technological innovation with ethical

safeguards and interdisciplinary design can lead to

emotion-aware transportation systems that reduce the

risk of road rage at scale.

AUTHORS CONTRIBUTION

All the authors contributed equally and their names

were listed in alphabetical order.

REFERENCES

Chai, C., Zhao, R., Shi, J., Zhou, J., & Yang, Z.: ‘The effect

of road environment and type of vehicles on road rage

in China.’ Journal of Transportation Safety & Security,

2022

Chris, T.: ‘Road rage skip operator removed from industry.’

Commercial Motor, 234(6045), 14-14. 2023

DePasquale, J., Geller, E., Clarke, S., et al. ‘Measuring road

rage: development of the Propensity for Angry Driving

Scale.’ Journal of Safety Research, 32(1), 1–16. 2001

Global, I. C.: ‘AI-driven road safety pilot report: Emotion-

aware interventions and real-time traffic management.’

2023

Jeon, M.: ‘Towards affect-integrated driving behaviour

research.’ Theoretical Issues in Ergonomics Science,

16(6), 553–585. 2015

Li, S., Wang, X., Zhang, Y., Li, H., & Xiang, H.: ‘Driver

road rage recognition based on improved MFCC fusion

feature and FA-PNN.’ Journal of Intelligent

Transportation Systems. 2022

National Traffic Safety Administration.: ‘Annual collision

report: Trends in road rage-related accidents.’ 2021

Ren, Q., Lu, X., Zhao, Y., Tang, Z., & Wu, H.: ‘Research

on the internal and external logic and influencing

factors of road rage.’ Journal of Safety Science and

Technology, 17(7), 162-166. 2021

The Effect of Road Rage Mood Changes on Driving Safety and Intelligent Regulation Strategies

Smith, J., & Doe, R.: ‘Personality traits and coping

strategies in road rage mitigation: A longitudinal

analysis.’ Transportation Psychology Review, 9(2), 75-

89. 2023

StevenLove, Y. M., & Grégoire, S. L.: ‘The Risks of Road

Rage: An Investigation Into the Influences of Driving‐

Related Anger on Driver Attention.’ Applied Cognitive

Psychology, 39(1), e70033-e70033. 2025

Subramanian, A., & Bhargavi, R.: ‘Generative AI and

Online Learning Based Road Rage and Aggressive

Driving Detection.’ International Journal of Intelligent

Transportation Systems Research,23(1),1-25. 2024

Subramanian, A., & Bhargavi, R.: ‘Road Rage and

Aggressive Driving Behaviour Detection in Usage-

Based Insurance Using Machine Learning.’

International Journal of Software Innovation

(IJSI),11(1),1-29. 2023

EMITI 2025 - International Conference on Engineering Management, Information Technology and Intelligence