Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Adolescents Based on Electroencephalogram Signals
arXiv:2603.00488v1 Announce Type: new Abstract: Adolescent pornography addiction requires early detection based on objective neurobiological biomarkers because self-report is prone to subjective bias due to social stigma. Conventional machine learning has not been able to model dynamic functional connectivity of the brain that fluctuates temporally during addictive stimulus exposure. This study proposes a state-of-the-art Dynamic Spatio-Temporal Graph Neural Network (DST-GNN) that integrates Phase Lag Index (PLI)-based Graph Attention Network (GAT) for spatial modeling and Bidirectional Gated Recurrent Unit (BiGRU) for temporal dynamics. The dataset consists of 14 adolescents (7 addicted, 7 healthy) with 19-channel EEG across 9 experimental conditions. Leave-One-Subject-Out Cross Validation (LOSO-CV) evaluation shows F1-Score of 71.00%$\pm$12.10% and recall of 85.71%, a 104% improvement compared to baseline. Ablation study confirms temporal contribution of 21% and PLI graph constructi
arXiv:2603.00488v1 Announce Type: new Abstract: Adolescent pornography addiction requires early detection based on objective neurobiological biomarkers because self-report is prone to subjective bias due to social stigma. Conventional machine learning has not been able to model dynamic functional connectivity of the brain that fluctuates temporally during addictive stimulus exposure. This study proposes a state-of-the-art Dynamic Spatio-Temporal Graph Neural Network (DST-GNN) that integrates Phase Lag Index (PLI)-based Graph Attention Network (GAT) for spatial modeling and Bidirectional Gated Recurrent Unit (BiGRU) for temporal dynamics. The dataset consists of 14 adolescents (7 addicted, 7 healthy) with 19-channel EEG across 9 experimental conditions. Leave-One-Subject-Out Cross Validation (LOSO-CV) evaluation shows F1-Score of 71.00%$\pm$12.10% and recall of 85.71%, a 104% improvement compared to baseline. Ablation study confirms temporal contribution of 21% and PLI graph construction of 57%. Frontal-central regions (Fz, Cz, C3, C4) are identified as dominant biomarkers with Beta contribution of 58.9% and Hjorth of 31.2%, while Cz-T7 connectivity is consistent as a trait-level biomarker for objective screening.
Executive Summary
This study proposes a Dynamic Spatio-Temporal Graph Neural Network (DST-GNN) for early detection of pornography addiction in adolescents using electroencephalogram (EEG) signals. The model integrates Phase Lag Index (PLI)-based Graph Attention Network (GAT) and Bidirectional Gated Recurrent Unit (BiGRU) to capture spatial and temporal dynamics. The results show a significant improvement in detection accuracy, with an F1-score of 71.00% and recall of 85.71%, outperforming baseline models. The study identifies frontal-central regions as dominant biomarkers and suggests the potential for objective screening.
Key Points
- ▸ Use of DST-GNN for early detection of pornography addiction in adolescents
- ▸ Integration of PLI-based GAT and BiGRU for spatial and temporal modeling
- ▸ Identification of frontal-central regions as dominant biomarkers
Merits
Innovative Approach
The study proposes a novel approach using DST-GNN, which can effectively capture the complex dynamics of brain activity in response to addictive stimuli.
Improved Detection Accuracy
The model achieves a significant improvement in detection accuracy, with an F1-score of 71.00% and recall of 85.71%, outperforming baseline models.
Demerits
Small Sample Size
The study uses a small sample size of 14 adolescents, which may limit the generalizability of the results.
Limited Experimental Conditions
The study uses a limited number of experimental conditions, which may not capture the full range of scenarios in which pornography addiction can occur.
Expert Commentary
This study makes a significant contribution to the field of neuroscience and machine learning, demonstrating the potential of DST-GNN for early detection of pornography addiction in adolescents. The use of PLI-based GAT and BiGRU allows for a more nuanced understanding of brain activity in response to addictive stimuli, and the identification of frontal-central regions as dominant biomarkers provides new insights into the neural mechanisms underlying addiction. However, further research is needed to validate the results and explore the potential applications of DST-GNN in clinical settings.
Recommendations
- ✓ Future studies should aim to replicate the results using larger sample sizes and more diverse experimental conditions
- ✓ Researchers should explore the potential of DST-GNN for detecting other types of addiction and mental health disorders