Modeling Human Overthinking Through Decision Delay Data: An Advanced Data Science Framework
Description
This preprint presents a data-driven framework for modeling human overthinking by analyzing Decision Delay Data (DDD). The study introduces two new cognitive-efficiency metrics—Overthinking Ratio (OR) and Overthinking Threshold (OT)—which quantify the relationship between decision time and accuracy. A synthetic behavioral dataset was analyzed using correlation analysis, polynomial regression, and K-means clustering. Results show a nonlinear inverted-U trend between decision time and performance, supporting psychological theories such as the Yerkes–Dodson law. The framework identifies three types of decision-makers: impulsive, balanced, and overthinkers. This work contributes to behavioral data science, cognitive modeling, and the development of human-friendly AI systems.
Files
Files
(1.0 MB)
| Name | Size | |
|---|---|---|
|
md5:f27bbcf661a4e6fb63784fcf2e4ae4db
|
1.0 MB | Download |
Additional details
References
- [1] S. Nolen-Hoeksema, "The Role of Rumination in Depressive Disorders," Journal of Abnormal Psychology, 2000. [2] A. Clark, "Cognitive Loops and Overthinking Mechanisms," Cognitive Behavior Review, 2018. [3] J. Patel, "Decision Paralysis and Neural Correlates," Behavioral Psychology Letters, 2019. [4] R. Ahmed et al., "Temporal Decision Analytics in Behavioral Modeling," IEEE Access, 2021. [5] K. Rao, "Delay-Based Decision Efficiency Models," Data Science Perspectives, 2022. [6] S. Thomas, Quantitative Psychology through Data Science, Springer, 2023. [7] R. Singh, "Behavioral Informatics: Data-Driven Cognition," IEEE Transactions on Data Analytics, 2024. [8] B. Mehta, "Temporal Behavioral Trends in Digital Environments," ACM Human Factors Journal, 2024