Implicit Cognition and Understanding Unobserved Human Mind States by Machines

Abstract

Humans can unconsciously develop abstract and complex knowledge from the encountered environment stimuli through implicit cognition and learning. In this paper, we examine whether a machine can recognize and establish such an unobserved capability. Using a mobile app for weight loss management to treat obesity as the context, we show that the machine can detect the occurrence of human implicit cognition and identify the dynamics of individual users’ unobserved mind states over time. Our empirical testing demonstrates that not all app users engage in implicit cognition and learning. A strong need for weight loss helps develop implicit cognition and learning. The occurrence of implicit learning promotes an activated mind state, and users in the activated state significantly increase their daily steps taken by 57.82% compared to those in the inactivated state when following the health suggestions in the app. Further, a simple home-screen reminder of checking the health suggestions in the app targeting inactivated state users will stimulate implicit learning, and increase their probabilities and time duration in the activated state by 29% and 38.9%, respectively. As a result, generating user mind state-based optimal healthcare interventions in the mobile app is shown to be quite effective.