Classifying High and Low Self-Esteem using a Novel Machine Learning Method Based on EEG Data

While self-esteem is an important concept for health, psychological well-being, and work success, correctly measuring self-esteem is a long-standing and unresolved problem. Here we propose a more objective measure of self-esteem based on electroencephalographic data. Using a novel machine learning approach analyzing specific fine-graded electroencephalographic sub- bands, we can correctly classify high and low self-esteem with an accuracy of over 79 percent, which represents a methodological landmark for health and information systems research. Our results have theoretical, methodological and practical implications.