Modeling temporality of human intentions by domain adaptation

Abstract

Categorizing a patient's intentions during clinical interactions in general and within motivational interviewing specifically may improve decision making in clinical treatments. Within this paper, we propose a method that models the temporal flow of a conversation and the transition between topics by using domain adaptation on a clinical dialogue corpus comprising Motivational Interviewing (MI) sessions. We deploy Bi-LSTM and topic models jointly to learn theme shifts across different time stages within these hour-long MI sessions to assess the patient's intent to change their habits or to sustain them respectively. Our experiments show promising results and improvements after considering temporality in the classification task over our baseline. This result confirms and extends related literature that has manually identified that certain phases within MI sessions are more predictive of patient outcomes than others.