ChatGPT-4o therapeutic chatbot may be as effective as journaling for relationship support

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot known as "Amanda" for relationship support shows that a single session of chatbot therapy can be as beneficial as evidence-based journaling in assisting with relationship conflict resolution.

These are the findings of a study published in PLOS Mental Health by Dr. Laura Vowels from the University of Lausanne, Switzerland, and the University of Roehampton, United Kingdom, and colleagues.

Recent research suggests LLMs may have the potential to act as an alternative or supplement to traditional talking therapy. In this study, Vowels and colleagues conducted a randomized controlled trial with participants in relationships who had identified an area of (non-abusive) relationship conflict, to compare the effectiveness of a single session with Amanda, a ChatGPT-4o chatbot prompted to act as an empathetic relationship therapist, versus a brief journaling task.

The authors recruited 258 participants initially, all of whom were 18 years or older and currently in a romantic relationship experiencing non-abusive conflict they hoped to address. (Any participants who mentioned thoughts of self-harm or abusive circumstances, or failed to identify a specific relationship conflict were excluded from the study).

Sign up for Blog Updates