Breathe Deep

Abstract

Mindfulness meditation has been demonstrated to be an effective approach for alleviating symptoms related to a variety of chronic health conditions, including pain, anxiety, and depression. Meditation takes practice and requires training, especially for novices, to learn mindfulness and emotion regulation. However, while face-to-face instructions can provide the best long-term results, many people cannot afford or schedule attendance at meditation classes. We present an automated conversational agent that acts as a virtual meditation coach that is interactive and adaptive to a user's breathing behavior, based on inputs from a respiration sensor in a meditation session. We designed and validated three interaction techniques based on the user's breathing. Results from two experimental studies demonstrate that users are highly receptive of the virtual coach technology, and appreciated the interactivity afforded by the respiration sensor. Participants also felt more relaxed when the meditation coach adapted the instructions to their breathing.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 47 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.