Detecting Change in Engineering Interest in Children through Machine Learning using Biometric Signals

© 2021 IEEE.Promoting interest in Science, Technology, Engineering, and Mathematics (STEM) is a worldwide priority. Thus, accurate measures of professional interest, an aspect of personality according to vocational theories, are necessary. There is empirical evidence supporting personality prediction using biometric signals. Therefore, professional interest may be estimated similarly. The objective of this study was to generate a machine learning algorithm based on physiological data of children performing engineering-related activities that estimated their professional interest in engineering subfields. Thirteen children between 6 and 15 years old participated. Using eight electroencephalographic channels, we measured electrodermal activity, heart rate variability, facial gestures, and body temperature in four 2-hour sessions as the children performed engineering-related educational activities. Psychometric tests evaluated their interest in specific engineering subfields per the activities. We processed the generated data to design a machine learning algorithm, which resulted in 80% precision in detecting the change in interest. The results indicate that a pattern for change in engineering interest exists and can be measured.

Detecting Change in Engineering Interest in Children through Machine Learning using Biometric Signals Academic Article in Scopus