Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion
This work addresses the need for accurate evaluation of MI therapy quality to improve behavioral change outcomes, representing an incremental advancement by applying multimodal fusion to an existing dataset.
The paper tackled the problem of classifying client utterances in Motivational Interviewing (MI) into change talk, sustain talk, or follow/neutral talk using multimodal features like text, prosody, facial expressivity, and body expressivity, achieving accurate classification and identifying key modalities for decision-making.
Motivational Interviewing (MI) is an approach to therapy that emphasizes collaboration and encourages behavioral change. To evaluate the quality of an MI conversation, client utterances can be classified using the MISC code as either change talk, sustain talk, or follow/neutral talk. The proportion of change talk in a MI conversation is positively correlated with therapy outcomes, making accurate classification of client utterances essential. In this paper, we present a classifier that accurately distinguishes between the three MISC classes (change talk, sustain talk, and follow/neutral talk) leveraging multimodal features such as text, prosody, facial expressivity, and body expressivity. To train our model, we perform annotations on the publicly available AnnoMI dataset to collect multimodal information, including text, audio, facial expressivity, and body expressivity. Furthermore, we identify the most important modalities in the decision-making process, providing valuable insights into the interplay of different modalities during a MI conversation.