Hybrid Deep Learning Models for Criminal Emotion Detection and Risk Prediction in Women's Safety
DOI:
https://doi.org/10.21015/vtcs.v14i1.2359Abstract
Crime against women is a persistent global issue, affecting women across all socio-economic backgrounds in various forms. Traditional crime prediction methods are typically reactive, being implemented only after a crime has occurred. This study proposes a hybrid deep-learning framework for detecting criminal emotions and estimating the risk of crimes against women. The model integrates several deep learning architectures, including CNN, Bi-LSTM, Bi-GRU, LSTM, and MLP. Additionally, two hybrid models, Bi-GRU + LSTM and CNN + Bi-LSTM, are introduced to enhance prediction performance. A dataset comprising 12465 real-world crime instances, including cases of domestic violence, sexual harassment, and acid attacks, was used for training and evaluation. The CNN + Bi-LSTM hybrid model achieved the highest accuracy at 98.12%, followed by the Bi-GRU + LSTM model with 97.65%. The individual model achieved performances were Bi-GRU (96.7%), CNN (94%), LSTM (96.3%), and Bi-LSTM (96.9%). The results demonstrate that the proposed model effectively captures both spatial features and temporal dependencies in crime-related data, offering promising capabilities for detecting emotional cues and assessing risk. Despite challenges such as data imbalance and privacy concerns, this study underscores the potential of AI-enabled solutions to enhance women’s safety and empower them with practical tools for crime prevention.
References
N. Maruyama, S. Horiuchi, and Y. Kataoka, “Prevalence and associated factors of intimate partner violence against pregnant women in urban areas of Japan: A cross-sectional study,” BMC Public Health, vol. 23, no. 1, p. 1168, 2023.
J. Raval, N. K. Jadav, S. Tanwar, G. Pau, F. Alqahtani, and A. Tolba, “Criminal emotion detection framework using convolutional neural network for public safety,” Scientific Reports, vol. 15, no. 1, p. 15279, 2025.
J. H. Michalski, “The definitional and methodological challenges of studying hate crimes: Evaluating official statistics, victimization, and self-report data,” in Research Handbook on Hate and Hate Crimes in Society. Edward Elgar Publishing, 2024, pp. 15–35.
L. Tampe and R. Bondu, “Assessing and reporting leaking of violent intent: Influences of perpetrator and witness characteristics,” European Journal of Criminology, vol. 20, no. 3, pp. 1164–1184, 2023.
T. T. Khoei and A. Singh, “A survey of Emotional Artificial Intelligence and crimes: Detection, prediction, challenges and future direction,” Journal of Computational Social Science, vol. 7, no. 3, pp. 2359–2402, 2024.
L. Spytska, “Psychological profile and prerequisites for the formation of the killer’s personality,” Social & Legal Studios, vol. 40, 2023.
S. Gu, “Deep learning-based prediction and intervention model for college students mental health status,” International Journal of High Speed Electronics and Systems, vol. 35, no. 3, p. 2540503, 2026.
K. G. Dhuri and S. Patil, “Crime prediction against women in surveillance videos using deep learning models: A review,” Computers and Electrical Engineering, vol. 128, p. 110651, 2025.
D. Kolhe and A. H. Bhat, “Crime and fraud at the community level: Social networking understanding into economic crimes and psychology motivations,” Journal of Social Sciences and Economics, vol. 3, no. 2, pp. 109–128, 2024.
O. Z. Apene, N. V. Blamah, and G. I. O. Aimufua, “Advancements in crime prevention and detection: From traditional approaches to artificial intelligence solutions,” European Journal of Applied Science, Engineering and Technology, vol. 2, no. 2, pp. 285–297, 2024.
T. A. Ojo and B. Ndzendze, African Women in the Fourth Industrial Revolution. Taylor & Francis, 2024.
R. M. Aziz, P. Sharma, and A. Hussain, “Machine learning algorithms for crime prediction under Indian penal code,” Annals of Data Science, vol. 11, no. 1, pp. 379–410, 2024.
S. Abokadr, A. Azman, H. Hamdan, and N. Amelina, “Handling imbalanced data for improved classification performance: Methods and challenges,” in Proc. 3rd Int. Conf. Emerging Smart Technologies and Applications (eSmarTA), 2023, pp. 1–8.
J. Raval, N. K. Jadav, S. Tanwar, G. Pau, F. Alqahtani, and A. Tolba, “Criminal emotion detection framework using convolutional neural network for public safety,” Scientific Reports, vol. 15, no. 1, p. 15279, 2025.
T. T. Khoei and A. Singh, “A survey of Emotional Artificial Intelligence and crimes: Detection, prediction, challenges and future direction,” Journal of Computational Social Science, vol. 7, no. 3, pp. 2359–2402, 2024.
S. Tam and O. O. Tanriver, “Multimodal deep learning crime prediction using tweets,” IEEE Access, vol. 11, pp. 93204–93214, 2023.
P. K. Saravag and B. R. Kumar, “A hybrid machine learning and regression approach for validating a multi-dimensional crime index in the context of crime against women,” IEEE Access, vol. 12, pp. 117955–117969, 2024.
R. Tamilkodi, B. Sujatha, and N. Leelavathy, “Emotion detection in text: Advances in sentiment analysis,” International Journal of System Assurance Engineering and Management, vol. 16, no. 2, pp. 552–560, 2025.
A. Manasa and S. Sen, “Interpretable predictions for crime categories using log loss approach for imbalanced target feature,” in Proc. IEEE Int. Conf. Contemporary Computing and Communications (InC4), 2024, pp. 1–6.
S. Venkatesh, “Crime prediction using machine learning and deep learning,” 2024.
Y. Gupta, “Optimizing urban safety: Leveraging vector databases, real-time sentiment analysis, and large language models for enhanced route planning and crime prevention,” 2024.
A. K. Kumar, P. Suganthi, S. Shanmugam, et al., “Empirical evaluation of video surveillance based crime and anomaly detection system using hybrid deep learning strategy,” in Proc. Int. Conf. Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), 2023, pp. 1–9.
V. Mandalapu, L. Elluri, P. Vyas, and N. Roy, “Crime prediction using machine learning and deep learning: A systematic review and future directions,” IEEE Access, vol. 11, pp. 60153–60170, 2023.
N. Iqbal, A. Hassan, and T. Waheed, “AI-driven crime prediction: A systematic literature review,” Journal of Computational Social Science, vol. 8, no. 2, p. 53, 2025.
M. A. Mannan, H. A. Ali, S. B. Kumar, and T. R. S. Gupta, “Evaluating the performance of machine learning classifier algorithms for software estimation in software development projects,” VFAST Transactions on Software Engineering, vol. 12, no. 1, pp. 70–78, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-By) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
