Temporal Personality Drift Prediction Using Behavioural Micro-Patterns
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V4I4P105Keywords:
Temporal Personality Drift, Big-Five Model, Behavioral Micro-Patterns, Concept Drift Adaptation, Smartphone Sensing, Within-Person Variability, Machine Learning, Longitudinal Prediction, Adaptive Ensemble, Personality StabilityAbstract
Temporal personality drift, the progressive change in an individual's big five scores over time, is a frontier challenge from a computational psychology, and adaptive machine learning perspective. Personality assessment paradigms are conventional and view personality types as fixed entities that ignore mean-level changes in personality documented over time and intra-personal variability in behavior. This synthesis explores the possibility of using phone-based behavior micro-patterns—such as communication frequencies, mobility signals, application usage log and intraday activity rhythm—as an input to a concept drift-aware predictive approach to model personality change trajectories up to 2020. The synthesis builds on literature which has shown that the rank-order trait consistency coefficients range from 0.43 in young adulthood to 0.65 in later life, and literature on smartphone sensing where AUC-ROC values for static trait prediction range from 0.78 to 0.84. The proposed Temporal Personality Drift Prediction (TPDP) architecture combines the adaptive ensemble classifiers with sliding-window temporal encoders. The results reveal that, when the features of variability in behavior are modeled across continuous 30-day sensing windows, they enhance the F1 score for drift detection by around 14 points compared to those based on cross-sectional baselines. Furthermore, concept drift adaptation mechanisms have been integrated into the framework, thus minimizing the degradation of performance by 9.2% to 2.8% for observation horizons of 12 months. Applicability ranges from mental health surveillance to adaptive recommender systems, and from longitudinal clinical assessments. Issues of data privacy, algorithmic fairness and temporal annotation are also explored.
References
[1] S. D. Gosling, P. J. Rentfrow, and W. B. Swann Jr., "A very brief measure of the Big-Five personality domains," J. Res. Pers., vol. 37, no. 6, pp. 504–528, 2003.
[2] B. W. Roberts and W. F. DelVecchio, "The rank-order consistency of personality traits from childhood to old age: A quantitative review of longitudinal studies," Psychol. Bull., vol. 126, no. 1, pp. 3–25, 2000.
[3] B. W. Roberts, K. E. Walton, and W. Viechtbauer, "Patterns of mean-level change in personality traits across the life course: A meta-analysis of longitudinal studies," Psychol. Bull., vol. 132, no. 1, pp. 1–25, 2006.
[4] G. M. Harari et al., "Sensing sociability: Individual differences in young adults' conversation, calling, texting, and app use behaviors in daily life," J. Pers. Soc. Psychol., vol. 119, no. 1, pp. 204–228, 2020.
[5] C. Stachl et al., "Predicting personality from patterns of behavior collected with smartphones," Proc. Natl. Acad. Sci., vol. 117, no. 30, pp. 17680–17687, 2020.
[6] D. Azucar, D. Marengo, and M. Settanni, "Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis," Pers. Individ. Differ., vol. 124, pp. 150–159, 2018.
[7] C. Stachl et al., "Predicting personality from patterns of behavior collected with smartphones," Proc. Natl. Acad. Sci., vol. 117, no. 30, pp. 17680–17687, 2020.
[8] J. Gama, I. Žliobaitė, A. Bifet, M. Pechenizkiy, and A. Bouchachia, "A survey on concept drift adaptation," ACM Comput. Surv., vol. 46, no. 4, Art. 44, 2014.
[9] J. Lu et al., "Learning under concept drift: A review," IEEE Trans. Knowl. Data Eng., vol. 31, no. 12, pp. 2346–2363, 2019.
[10] B. W. Roberts and D. Mroczek, "Personality trait change in adulthood," Curr. Dir. Psychol. Sci., vol. 17, no. 1, pp. 31–35, 2008.
[11] W. Wang et al., "Sensing behavioral change over time: Using within-person variability features from mobile sensing to predict personality traits," Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 2, no. 3, Art. 141, 2018.
[12] M. Kosinski, D. Stillwell, and T. Graepel, "Private traits and attributes are predictable from digital records of human behavior," Proc. Natl. Acad. Sci., vol. 110, no. 15, pp. 5802–5805, 2013.
[13] W. Youyou, M. Kosinski, and D. Stillwell, "Computer-based personality judgments are more accurate than those made by humans," Proc. Natl. Acad. Sci., vol. 112, no. 4, pp. 1036–1040, 2015.
[14] Y. Mehta, N. Majumder, A. Gelbukh, and E. Cambria, "Recent trends in deep learning based personality detection," Artif. Intell. Rev., vol. 53, no. 4, pp. 2313–2339, 2020.
[15] H. L. Dotterer et al., "Personalized models of personality disorders: Using a temporal network method to understand symptomatology and daily functioning in a clinical sample," Psychol. Med., vol. 50, no. 14, pp. 2397–2405, 2020.
[16] J. Hinds and A. Joinson, "Human and computer personality prediction from digital footprints," Curr. Dir. Psychol. Sci., vol. 28, no. 2, pp. 204–211, 2019.
[17] C. Stachl et al., "Personality research and assessment in the era of machine learning," Eur. J. Pers., vol. 34, no. 5, pp. 613–631, 2020.
[18] R. R. McCrae and P. T. Costa Jr., "The stability of personality: Observations and evaluations," Curr. Dir. Psychol. Sci., vol. 3, no. 6, pp. 173–175, 1994.
[19] M. Settanni, D. Azucar, and D. Marengo, "Predicting individual characteristics from digital traces on social media: A meta-analysis," Cyberpsychol. Behav. Soc. Netw., vol. 21, no. 4, pp. 217–228, 2018
[20] Taluri, R. (2021). Cloud-Native Architectures for Enterprise Financial Data Management, Analytics, and Regulatory Reporting Compliance. International Journal of Emerging Trends in Computer Science and Information Technology, 2(2), 101-111. https://doi.org/10.63282/3050-9246.IJETCSIT-V2I2P112
