An Intelligent Approach Using Machine Learning Techniques to Predict Flow in People
M. C. Pegalajar, L. G. B. Ruiz, E. Pérez-Moreiras, J. Boada-Grau, M. J. Serrano-Fernandez
Big Data and Cognitive Computing June 27, 2023 DOI: 10.3390/bdcc7020067 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Observational study Peer reviewed |
|---|---|
| Keywords | Machine learning Artificial neural networks Flow Data mining |
| Key findings | A multi-layer perceptron neural network estimates Flow state with 88.58% accuracy using personality trait variables. |
Abstract
The goal of this study is to estimate the state of consciousness known as Flow, which is associated with an optimal experience and can indicate a person’s efficiency in both personal and professional settings. To predict Flow, we employ artificial intelligence techniques using a set of variables not directly connected with its construct. We analyse a significant amount of data from psychological tests that measure various personality traits. Data mining techniques support conclusions drawn from the psychological study. We apply linear regression, regression tree, random forest, support vector machine, and artificial neural networks. The results show that the multi-layer perceptron network is the best estimator, with an MSE of 0.007122 and an accuracy of 88.58%. Our approach offers a novel perspective on the relationship between personality and the state of consciousness known as Flow.