Leveraging Machine Learning to Enhance Road Safety: A Social Marketing Approach
Main Article Content
Abstract
Road safety remains a critical concern worldwide. This research aims to investigate the use of Explainable AI (XAI) techniques, particularly SHAP (Shapley Additive Explanations), to identify key factors influencing road accident severity and create a social marketing campaign encouraging people to change their behavior in relation to road safety. Several machine learning models were developed using data from Thailand’s Ministry of Transport. The results show that the Light Gradient Boosting Machine (LGBM) model achieved the highest accuracy of 0.85 and an F1 score of 0.83. SHAP analysis revealed that the most significant contributing factors were the number of motorcycle involvements, road code, and the total number of vehicles and people involved in the accident. A practical framework for promoting sustainable road safety was proposed, focusing on raising awareness, delivering emotionally impactful communication, and fostering immediate behavioral change. This research provides valuable insights for strategic road safety initiatives and demonstrates the effectiveness of integrating machine learning with XAI. The findings can guide government authorities, policymakers, insurance companies, and social marketing planners in improving road safety.
Article Details
References
Aboulola, O. I., Alabdulqader, E. A., AlArfaj, A. A., Alsubai, S., & Kim, T. H. (2024). An Automated Approach for Predicting Road Traffic Accident Severity Using Transformer Learning and Explainable AI Technique. IEEE Access, 12, 61062-61072. https://doi.org/10.1109/ACCESS.2024.3380895
Ahmed, S., Hossain, M. A., Ray, S. K., Bhuiyan, M. M. I., & Sabuj, S. R. (2023). A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance. Transportation Research Interdisciplinary Perspectives, 19, 100814. https://doi.org/https://doi.org/10.1016/j.trip.2023.100814
Ali, F., Ali, A., Imran, M., Naqvi, R. A., Siddiqi, M. H., & Kwak, K.-S. (2021). Traffic accident detection and condition analysis based on social networking data. Accident Analysis & Prevention, 151, 105973. https://doi.org/https://doi.org/10.1016/j.aap.2021.105973
Alkhawaldeh, I. M., Albalkhi, I., & Naswhan, A. J. (2023). Challenges and limitations of synthetic minority oversampling techniques in machine learning. World J Methodol, 13(5), 373-378. https://doi.org/10.5662/wjm.v13.i5.373
Arvin, R., Khattak, A. J., & Qi, H. (2021). Safety critical event prediction through unified analysis of driver and vehicle volatilities: Application of deep learning methods. Accident Analysis & Prevention, 151, 105949. https://doi.org/https://doi.org/10.1016/j.aap.2020.105949
Barrie, L. R., Jones, S. C., & Wiese, E. (2011). “At Least I’M Not Drink-Driving”: Formative Research for a Social Marketing Campaign to Reduce Drug-Driving among Young Drivers. Australasian Marketing Journal, 19(1), 71-75. https://doi.org/10.1016/j.ausmj.2010.11.010
Berhanu, Y., Schröder, D., Wodajo, B. T., & Alemayehu, E. (2024). Machine learning for predictions of road traffic accidents and spatial network analysis for safe routing on accident and congestion-prone road networks. Results in Engineering, 23, 102737. https://doi.org/https://doi.org/10.1016/j.rineng.2024.102737
Betsch, C., Ulshöfer, C., Renkewitz, F., & Betsch, T. (2011). The Influence of Narrative v. Statistical Information on Perceiving Vaccination Risks. Medical Decision Making, 31(5), 742-753. https://doi.org/10.1177/0272989x11400419
Bryant, C. A., Forthofer, M. S., Brown, K. R. M., Landis, D. C., & McDermott, R. J. (2000). Community-based prevention marketing: the next steps in disseminating behavior change. American Journal of Health Behavior, 24(1), 61-68.
Buyucek, N., Kubacki, K., Rundle-Thiele, S., & Pang, B. (2016). A systematic review of stakeholder involvement in social marketing interventions. Australasian Marketing Journal, 24(1), 8-19.
Campbell, B., Heitner, J., Amos Mwelelo, P., Fogel, A., Mujumdar, V., Adams, L. V., Boniface, R., & Su, Y. (2022). Impact of SMS text messaging reminders on helmet use among motorcycle drivers in Dar es Salaam, Tanzania: randomized controlled trial. Journal of Medical Internet Research, 24(4), e27387.
Charyk Stewart, T., Edwards, J., Penney, A., Gilliland, J., Clark, A., Haidar, T., Batey, B., Pfeffer, A., Fraser, D. D., Merritt, N. H., & Parry, N. G. (2021). Evaluation of a population health strategy to reduce distracted driving: Examining all “Es” of injury prevention. Journal of Trauma and Acute Care Surgery, 90(3), 535-543. https://doi.org/10.1097/ta.0000000000002948
Chen, J., Tao, W., Jing, Z., Wang, P., & Jin, Y. (2024). Traffic accident duration prediction using multi-mode data and ensemble deep learning. Heliyon, 10(4). https://doi.org/10.1016/j.heliyon.2024.e25957
Cooper, C. (2007). Successfully Changing Individual Travel Behavior:Applying Community-Based Social Marketing to Travel Choice. Transportation Research Record, 2021(1), 89-99. https://doi.org/10.3141/2021-11
Crawshaw, P. (2014). Changing Behaviours, Improving Outcomes? Governing Healthy Lifestyles Through Social Marketing. Sociology Compass, 8(9), 1127-1139. https://doi.org/https://doi.org/10.1111/soc4.12196
Davis, K. C., Shafer, P. R., Rodes, R., Kim, A., Hansen, H., Patel, D., Coln, C., & Beistle, D. (2016). Does Digital Video Advertising Increase Population-Level Reach of Multimedia Campaigns? Evidence From the 2013 Tips From Former Smokers Campaign. J Med Internet Res, 18(9), e235. https://doi.org/10.2196/jmir.5683
Diegelmann, S., Ninaus, K., & Terlutter, R. (2020). Distracted driving prevention: an analysis of recent UK campaigns. Journal of Social Marketing, 10(2), 243-264. https://doi.org/10.1108/JSOCM-07-2019-0105
Elias, W. (2021). The effectiveness of different incentive programs to encourage safe driving. Sustainability, 13(6), 3398.
Elreedy, D., Atiya, A. F., & Kamalov, F. (2024). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 113(7), 4903-4923. https://doi.org/10.1007/s10994-022-06296-4
Feng, Y., Wang, X., Chen, Q., Yang, Z., Wang, J., Li, H., Xia, G., & Liu, Z. (2024). Prediction of the severity of marine accidents using improved machine learning. Transportation Research Part E: Logistics and Transportation Review, 188, 103647. https://doi.org/https://doi.org/10.1016/j.tre.2024.103647
Flaherty, T., Domegan, C., Duane, S., Brychkov, D., & Anand, M. (2020). Systems social marketing and macro-social marketing: A systematic review. Social Marketing Quarterly, 26(2), 146-166.
Fox, K. F. A., & Kotler, P. (1980). The Marketing of Social Causes: The First 10 Years. Journal of Marketing, 44(4), 24-33. https://doi.org/10.1177/002224298004400404
Hu, J., Huang, M.-C., & Yu, X. (2020). Efficient mapping of crash risk at intersections with connected vehicle data and deep learning models. Accident Analysis & Prevention, 144, 105665.
Kok, İ., Okay, F. Y., Özgecan, M., & Özdemir, S. (2023). Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey. IEEE Internet of Things Journal, 10(16), 14764-14779. https://doi.org/10.1109/JIOT.2023.3287678
Isler, C. A., Huang, Y., & de Melo, L. E. A. (2024). Developing accident frequency prediction models for urban roads: A case study in São Paulo, Brazil. IATSS Research, 48(3), 378-392. https://doi.org/https://doi.org/10.1016/j.iatssr.2024.07.002
Javeed, D., Gao, T., Kumar, P., & Jolfaei, A. (2024). An Explainable and Resilient Intrusion Detection System for Industry 5.0. IEEE Transactions on Consumer Electronics, 70(1), 1342-1350. https://doi.org/10.1109/TCE.2023.3283704
Kashevnik, A., Lashkov, I., & Gurtov, A. (2020). Methodology and Mobile Application for Driver Behavior Analysis and Accident Prevention. IEEE Transactions on Intelligent Transportation Systems, 21(6), 2427-2436. https://doi.org/10.1109/TITS.2019.2918328
Kiptoo, I. K., Kariuki, S. N., & Ocharo, K. N. (2021). Risk management and financial performance of insurance firms in Kenya. Cogent Business & Management, 8(1), 1997246. https://doi.org/10.1080/23311975.2021.1997246
Kumar, R., Javeed, D., Aljuhani, A., Jolfaei, A., Kumar, P., & Islam, A. K. M. N. (2024). Blockchain-Based Authentication and Explainable AI for Securing Consumer IoT Applications. IEEE Transactions on Consumer Electronics, 70(1), 1145-1154. https://doi.org/10.1109/TCE.2023.3320157
Lee, H., Lee, J., & Chung, Y. (2022). Traffic density estimation using vehicle sensor data. Journal of Intelligent Transportation Systems, 26(6), 675-689. https://doi.org/10.1080/15472450.2021.1966626
Luca, N. R., Hibbert, S., & McDonald, R. (2016). Midstream value creation in social marketing. Journal of Marketing Management, 32(11-12), 1145-1173. https://doi.org/10.1080/0267257X.2016.1190777
Ma, Y., Xie, Z., Chen, S., Wu, Y., & Qiao, F. (2022). Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion. International Journal of Environmental Research and Public Health, 19(1), 348. https://www.mdpi.com/1660-4601/19/1/348
Matsumoto, D. (2007). Culture, Context, and Behavior. Journal of Personality, 75(6), 1285-1320. https://doi.org/https://doi.org/10.1111/j.1467-6494.2007.00476.x
Ministry of Transport. (2024). Accidents on Ministry of Transport’s Road Network. https://datagov.mot.go.th/dataset/roadaccident
Muleme, J., Kankya, C., Ssempebwa, J. C., Mazeri, S., & Muwonge, A. (2017). A framework for integrating qualitative and quantitative data in knowledge, attitude, and practice studies: a case study of pesticide usage in eastern Uganda. Frontiers in Public Health, 5, 318.
Napontun, K., & Senachai, P. (2023). Identifying factors influencing consumers not to skip TrueView advertising on YouTube. ABAC Journal, 43(1), 85-102. https://doi.org/10.14456/abacj.2023.6
Obasi, I. C., & Benson, C. (2023). Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents. Heliyon, 9(8), e18812. https://doi.org/https://doi.org/10.1016/j.heliyon.2023.e18812
Omerustaoglu, F., Sakar, C. O., & Kar, G. (2020). Distracted driver detection by combining in-vehicle and image data using deep learning. Applied Soft Computing, 96, 106657. https://doi.org/https://doi.org/10.1016/j.asoc.2020.106657
Pei, Y., Wen, Y., & Pan, S. (2024). Road Traffic Accident Risk Prediction and Key Factor Identification Framework Based on Explainable Deep Learning. IEEE Access, PP, 1-1. https://doi.org/10.1109/ACCESS.2024.3451522
Perafan-Villota, J. C., Mondragon, O. H., & Mayor-Toro, W. M. (2022). Fast and Precise: Parallel Processing of Vehicle Traffic Videos Using Big Data Analytics. IEEE Transactions on Intelligent Transportation Systems, 23(8), 12064-12073. https://doi.org/10.1109/TITS.2021.3109625
Plant, B. R. C., Irwin, J. D., & Chekaluk, E. (2017). The effects of anti-speeding advertisements on the simulated driving behaviour of young drivers. Accident Analysis & Prevention, 100, 65-74. https://doi.org/https://doi.org/10.1016/j.aap.2017.01.003
Ratanawimon, S., & Tanawongsuwan, P. (2024, August 19 - 21, 2024). Prediction of Severity Level of Road Traffic Accident in Thailand using Machine Learning. Proceedings of the 10th World Congress on Electrical Engineering and Computer Systems and Sciences (EECSS’24), Barcelona, Spain.
Roger, A., Dourgoudian, M., Mergey, V., Laplanche, D., Ecarnot, F., & Sanchez, S. (2023). Effectiveness of prevention interventions using social marketing methods on behavioural change in the general population: a systematic review of the literature. International Journal of Environmental Research and Public Health, 20(5), 4576.
Sahlaoui, H., Alaoui, E. A. A., Nayyar, A., Agoujil, S., & Jaber, M. M. (2021). Predicting and Interpreting Student Performance Using Ensemble Models and Shapley Additive Explanations. IEEE Access, 9, 152688-152703. https://doi.org/10.1109/ACCESS.2021.3124270
Senachai, P., Julsrigival, J., & Sann, R. (2022). Social Marketing Strategy to Promote Traditional Thai Medicines during COVID-19: KAP and DoI Two-Step Theory Application Process. International Journal of Environmental Research and Public Health, 19(14), 8416.
Shaik, M. E., Islam, M. M., & Hossain, Q. S. (2021). A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies, 7, 100040. https://doi.org/https://doi.org/10.1016/j.eastsj.2021.100040
Shams, M., Maleki, M., Shariatinia, S., Omidimorad, A., Zakeri, H., Fallah Zavareh, M., Hamelmann, C., Mooren, L., Shuey, R., & Ranjbar, M. (2022). Insights for speed management among Iranian drivers: a social marketing formative research study. Journal of Injury and Violence Research, 14(3), 199-208. https://doi.org/10.5249/jivr.v14i3.1690
Siebert, F. W., Hellmann, L., Pant, P. R., Lin, H., & Trimpop, R. (2021). Disparity of motorcycle helmet use in Nepal – Weak law enforcement or riders’ reluctance? Transportation Research Part F: Traffic Psychology and Behaviour, 79, 72-83. https://doi.org/https://doi.org/10.1016/j.trf.2021.04.005
Spilbergs, A., Fomins, A., & Krastiņš, M. (2022). Multivariate Modelling of Motor Third Party Liability Insurance Claims. European Journal of Business Science and Technology, 8(1), 5-18.
Sufian, M. A., Varadarajan, J., & Niu, M. (2024). Enhancing prediction and analysis of UK road traffic accident severity using AI: Integration of machine learning, econometric techniques, and time series forecasting in public health research. Heliyon, 10(7), e28547. https://doi.org/https://doi.org/10.1016/j.heliyon.2024.e28547
Tapp, A., Ursachi, G. M., & Campsall, D. (2023). Exploring the relationship between car brands and risky driving. Journal of Social Marketing, 13(4), 554-571. https://doi.org/10.1108/JSOCM-04-2023-0074
Troy, D. M., Maynard, O. M., Hickman, M., Attwood, A. S., & Munafò, M. R. (2015). The effect of glass shape on alcohol consumption in a naturalistic setting: a feasibility study. Pilot and Feasibility Studies, 1(1), 27. https://doi.org/10.1186/s40814-015-0022-2
Truong, V. D. (2014). Social Marketing:A Systematic Review of Research 1998–2012. Social Marketing Quarterly, 20(1), 15-34. https://doi.org/10.1177/1524500413517666
Truong, V. D., & Hall, C. M. (2013). Social Marketing and Tourism:What Is the Evidence? Social Marketing Quarterly, 19(2), 110-135. https://doi.org/10.1177/1524500413484452
Valente, T. W., Paredes, P., & Poppe, P. R. (1998). Matching the Message to the Process: The Relative Ordering of Knowledge, Attitudes, and Practices in Behavior Change Research. Human Communication Research, 24(3), 366-385. https://doi.org/10.1111/j.1468-2958.1998.tb00421.x
Venkatesh Raja, K., Siddharth, R., Yuvaraj, S., & Ramesh Kumar, K. A. (2023). An Artificial Intelligence based automated case-based reasoning (CBR) system for severity investigation and root-cause analysis of road accidents – Comparative analysis with the predictions of ChatGPT. Journal of Engineering Research. https://doi.org/https://doi.org/10.1016/j.jer.2023.09.019
Viswanath, D., P, K., N, R., & B, R. (2021, 8-10 April 2021). A Road Accident Prediction Model Using Data Mining Techniques. 2021 5th International Conference on Computing Methodologies and Communication (ICCMC),
von Beesten, S., & Bresges, A. (2022). Effectiveness of road safety prevention in schools. Frontiers in Psychology, 13, 1046403.
Wang, B., Zhan, S., Sun, J., & Lee, L. (2009). Social mobilization and social marketing to promote NaFeEDTA-fortified soya sauce in an iron-deficient population through a public–private partnership. Public Health Nutrition, 12(10), 1751-1759. https://doi.org/10.1017/S136898000800431X
Wang, G., Li, J., Shen, L., Ding, S., Shi, Z., & Zuo, F. (2024). Towards efficient and accurate prediction of freeway accident severity using two-level fuzzy comprehensive evaluation. Heliyon, 10(16), e36396. https://doi.org/https://doi.org/10.1016/j.heliyon.2024.e36396
Wetchayont, P. (2021). Investigation on the Impacts of COVID-19 Lockdown and Influencing Factors on Air Quality in Greater Bangkok, Thailand. Advances in Meteorology, 2021, 1-11. https://doi.org/10.1155/2021/6697707
World Health Organization. (2023, 13 December 2023). Global status report on road safety 2023. https://www.who.int/teams/social-determinants-of-health/safety-and-mobility/global-status-report-on-road-safety-2023
Zhankaziev, S. V., Zamytskih, A. V., Vorobyev, A. I., Gavrilyuk, M. V., & Pletnev, M. G. (2022, 10-11 Nov. 2022). Predicting Traffic Accidents Using the Conflict Coefficient. 2022 Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex (TIRVED)
Zhao, H., Yu, H., Li, D., Mao, T., & Zhu, H. (2019). Vehicle Accident Risk Prediction Based on AdaBoost-SO in VANETs. IEEE Access, 7, 14549-14557. https://doi.org/10.1109/ACCESS.2019.2894176
Zheng, S., Zhao, L., Ju, N., Hua, T., Zhang, S., & Liao, S. (2021). Relationship between oral health-related knowledge, attitudes, practice, self-rated oral health and oral health-related quality of life among Chinese college students: a structural equation modeling approach. BMC Oral Health, 21(1), 99. https://doi.org/10.1186/s12903-021-01419-0