Head Matters: Explainable Human-centered Trait Prediction from Head Motion Dynamics
This work addresses explainable trait prediction for human-centered behavioral analytics, but it is incremental as it builds on existing methods like LSTM and FACS.
The paper tackled predicting personality and interview traits from head motion dynamics by using kinemes and FACS features, achieving accurate predictions with LSTM networks performing similarly to CNNs and performance affected by observation time-length.
We demonstrate the utility of elementary head-motion units termed kinemes for behavioral analytics to predict personality and interview traits. Transforming head-motion patterns into a sequence of kinemes facilitates discovery of latent temporal signatures characterizing the targeted traits, thereby enabling both efficient and explainable trait prediction. Utilizing Kinemes and Facial Action Coding System (FACS) features to predict (a) OCEAN personality traits on the First Impressions Candidate Screening videos, and (b) Interview traits on the MIT dataset, we note that: (1) A Long-Short Term Memory (LSTM) network trained with kineme sequences performs better than or similar to a Convolutional Neural Network (CNN) trained with facial images; (2) Accurate predictions and explanations are achieved on combining FACS action units (AUs) with kinemes, and (3) Prediction performance is affected by the time-length over which head and facial movements are observed.