Identifying Mood Episodes Using Dialogue Features from Clinical Interviews

TL;DR

This paper explores how dialogue features from clinical interviews can be used to automatically identify mood episodes in bipolar disorder, enhancing current assessment methods by incorporating interactive speech patterns.

Contribution

It introduces the use of higher-level interactive dialogue features alongside acoustic data for improved automatic mood episode detection.

Findings

Dialogue features improve mood episode recognition accuracy

Interactive patterns vary significantly across mood states

Combining dialogue and acoustic features enhances prediction performance

Abstract

Bipolar disorder, a severe chronic mental illness characterized by pathological mood swings from depression to mania, requires ongoing symptom severity tracking to both guide and measure treatments that are critical for maintaining long-term health. Mental health professionals assess symptom severity through semi-structured clinical interviews. During these interviews, they observe their patients' spoken behaviors, including both what the patients say and how they say it. In this work, we move beyond acoustic and lexical information, investigating how higher-level interactive patterns also change during mood episodes. We then perform a secondary analysis, asking if these interactive patterns, measured through dialogue features, can be used in conjunction with acoustic features to automatically recognize mood episodes. Our results show that it is beneficial to consider dialogue features when analyzing and building automated systems for predicting and monitoring mood.