โก Quick Summary
This study explores the complex relationship between digital behavior and substance use risk, utilizing multiple datasets to uncover how demographic factors and psychological states influence substance use behaviors. The findings suggest that anxiety and loneliness are significantly impacted by social media engagement, challenging traditional assumptions about digital interactions.
๐ Key Details
- ๐ Datasets Used: NHANES dataset and Kaggle social media psychology dataset
- ๐งฉ Sample Size: Supplementary survey with N = 236 participants
- โ๏ธ Technologies: Machine learning models including Random Forest, XGBoost, AdaBoost, SVR, and Logistic Regression
- ๐ Performance: Improved predictive performance after hyperparameter tuning
๐ Key Takeaways
- ๐ Nonlinear relationships were found between social media engagement, anxiety, and loneliness.
- ๐ก Anxiety scores plateaued at higher levels of digital engagement, indicating qualitative interactions matter more than duration.
- ๐ค Machine learning models showed enhanced predictive capabilities after tuning.
- ๐ The study emphasizes the need for platform-specific digital well-being strategies.
- ๐ Multi-source evidence framework proposed for future behavioral risk profiling.
- ๐ Findings support culturally sensitive interventions integrating behavioral data and user experiences.

๐ Background
Substance use remains a multifaceted public health challenge, increasingly influenced by both traditional behavioral triggers and the rise of digital interactions. Understanding how these elements intertwine is crucial for developing effective prevention strategies. This study aims to bridge the gap between digital behavior and substance use risk, providing insights that can inform future research and interventions.
๐๏ธ Study
The research utilized a combination of quantitative analyses from the NHANES dataset and a Kaggle social media psychology dataset to explore the connections between demographic factors, psychological states, and digital engagement patterns. A supplementary survey was conducted to add qualitative context to the findings, enriching the understanding of how digital behavior relates to substance use risk.
๐ Results
The analysis revealed that the relationship between social media engagement and psychological distress is more complex than previously thought. Specifically, while increased digital engagement was expected to correlate with higher anxiety levels, the results indicated that anxiety scores plateaued at higher engagement levels. This suggests that the nature of online interactions may play a more significant role in psychological outcomes than the sheer amount of time spent online.
๐ Impact and Implications
The findings from this study have significant implications for public health strategies. By recognizing the importance of digital engagement patterns alongside traditional behavioral and demographic factors, researchers and practitioners can develop more nuanced and effective interventions. This could lead to the creation of tailored digital well-being strategies that address the unique challenges posed by online interactions, ultimately contributing to better mental health outcomes and reduced substance use risk.
๐ฎ Conclusion
This study highlights the critical need to consider both digital behavior and psychological factors in substance use research. The proposed multi-source evidence framework lays the groundwork for future explorations into behavioral risk profiling and prevention systems. As we continue to navigate the complexities of digital interactions, integrating these insights into public health strategies will be essential for fostering healthier communities.
๐ฌ Your comments
What are your thoughts on the relationship between digital behavior and substance use? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
A multi-dataset exploratory framework for understanding digital behavior and substance use risk profiles.
Abstract
INTRODUCTION: Substance use continues to evolve as a multidimensional public health challenge influenced by traditional behavioral triggers and emerging digital interactions. This study investigates how demographic factors, psychological states, and patterns of digital engagement shape substance use behaviors using multiple behavioral data sources.
METHODS: Quantitative analyses were conducted using the NHANES dataset and a Kaggle social media psychology dataset to identify statistical relationships and train predictive machine learning models for substance use indicators and digital behavioral patterns. Random Forest, XGBoost, AdaBoost, Support Vector Regression (SVR), and Logistic Regression models were evaluated, with hyperparameter tuning applied to improve predictive performance. In addition, a supplementary survey (N = 236) was collected and used as a qualitative interpretive layer to contextualize the relationship between digital behavior and substance use risk.
RESULTS: The analysis revealed nonlinear relationships between social media engagement, anxiety, and loneliness. Contrary to the widely cited linear dose-response assumption, anxiety scores plateaued at higher levels of digital engagement, suggesting that the qualitative nature of online interactions may exert greater influence on psychological distress than usage duration alone. Machine learning models demonstrated improved predictive performance after hyperparameter tuning across both datasets.
DISCUSSION: These findings highlight the importance of considering digital engagement patterns alongside traditional behavioral and demographic factors in substance use research. The results support the development of platform-specific digital well-being strategies, nuanced behavioral modeling approaches, and culturally sensitive interventions that integrate both objective behavioral data and subjective user experiences. The proposed multi-source evidence framework provides a foundation for future exploratory behavioral risk profiling and prevention systems.
Author: [‘Sindhu PS’, ‘Narendra M’]
Journal: Front Public Health
Citation: Sindhu PS and Narendra M. A multi-dataset exploratory framework for understanding digital behavior and substance use risk profiles. A multi-dataset exploratory framework for understanding digital behavior and substance use risk profiles. 2026; 14:1771271. doi: 10.3389/fpubh.2026.1771271