Predicting Trust Between People

Date: December 2013

JJ Lee, WB Knox, JB Wormwood, C Breazeal, D DeSteno (2013).
Computationally Modeling Interpersonal Trust.
Frontiers in Psychology.

Jin Joo Lee. Modeling the Dynamics of Nonverbal Behavior on Interpersonal Trust for Human-Robot Interactions. Masters Thesis, Massachusetts Institute of Technology, 2011.

HMM Models
Through the construction and simulation of hidden Markov models (HMMs), I investigated the sequential interplay of low-trust and high-trust nonverbal behaviors.

My computational trust model is capable of predicting—above human accuracy—the degree of trust a person has toward a stranger by observing the nonverbal behaviors expressed in their social interaction. I used machine learning algorithms, specifically hidden Markov models (HMMs), to model the temporal relationship between specific nonverbal behaviors. By interpreting its resulting learned structure, I discovered that the sequence of low and high trusting behaviors a person emits provides further information of their trust orientation toward their partner. These discoveries shaped the feature engineering process that enabled a support vector machine (SVM) model to achieve a prediction performance more accurate than human judgment.

Machine Learning Pipeline
Domain knowledge when incorporated into the feature selection process permits a SVM model to outperform human judgement.