Analyzing the Differences in Human Reasoning via Joint Nonnegative Matrix Factorization
- Daniel Brand, Cognitive Computation Lab, University of Freiburg, Freiburg, Germany
- Nicolas Riesterer, Cognitive Computation Lab, University of Freiburg, Freiburg, Germany
- Hannah Dames, Cognitive Computation Lab, University of Freiburg, Freiburg, Germany
- Marco Ragni, Cognitive Computation Lab, University of Freiburg, Freiburg, Germany
AbstractJoint Nonnegative Matrix Factorization (JNMF) is a method for factor analysis that is capable of simultaneously decomposing two datasets into related latent state representations. Enabling factor analysis for contrasting applications, i.e., to find common and distinct structural patterns in data, JNMF has great potential for use in the field of cognitive science. Applied to experimental data, JNMF allows for the extraction of common and distinct patterns of behavior thereby extending the outcomes of traditional correlation-based contrasting methods. In this article, we introduce JNMF to the field of cognitive science and demonstrate its potential on the exemplary domain of syllogistic reasoning by comparing reasoning patterns for different personality factors. Results are interpreted with respect to the theoretical state of the art in syllogistic reasoning research.