Voice Assistant-Based CBT for Depression in Students: Effects of Empathy-Driven Dialog Management.

With a rising number of students with depression, new low-threshold solutions have to be found to strengthen the resilience against and help those affected by mental disorders. One approach lies in the usage of chatbots (CBs) to provide tools based in cognitive behavioral therapy (CBT) that can be used independently in order to reduce symptoms of depression. To ensure the adherence to such systems, a good usability and acceptance is important. Conversational agents (CAs) that provide CBT-based content should further be sensitive to the users emotional state, as empathy is one central aspect of therapy. While promising research has been going on in the feld of CB-based empathy-driven CBT, voice assistant-based (VA-based) solutions have thus far not been investigated deeply. Therefore, we propose a VA-based, empathy-driven system, capable of delivering selected methods from CBT to students with depression. To assess the effects of empathy-driven dialog management on perceived usability and acceptance, we conducted a single blind randomized controlled A/B testing experiment with 10 participants. While the application of empathetical dialog management shows no benefts to the usability and acceptance, results overall indicate a good usability and acceptance of the system in the target group.