Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed a novel software tool that leverages artificial intelligence to assist with a user’s expressive writing process.
Background: With the recent rise in mental health diagnoses and awareness, there is a higher demand for mental health services which has not yet been met. Access to clinical mental health services is challenging for many people due to cost, availability, and time constraints from jobs or family commitments. One alternative to the standard-of-care talk therapy is expressive writing, much like journaling or diary keeping. In addition, recent advances in generative AI with the rise of ChatGPT and other tools, can potentially be leveraged for counseling and therapy purposes. However, such tools have not been fully utilized to provide users both freedom of expression and interactive feedback in expressive writing exercises. Combining advances in AI with expressive writing exercises may provide powerful mental health benefits to users. There is a demonstrated need for an accessible method to allow users to express and process emotions with real-time feedback in expressive writing exercises.
Innovation: To address these concerns, Professor Xiang Chen and his team have developed a novel software in conjunction with mental health clinicians to help users understand and reframe emotions. The three methods to do so include prompting the user when they struggle to continue writing, highlighting significant emotions present in the writing, and deploying a method to reframe negatively phrased portions in a more positive light. This allows users to work on their mental health without access to clinicians, leveraging advancements in generative AI for a positive mental health outcome.
Potential Applications: • Talk therapy replacement or augmentation • Tracking method for long in-patient stays in medical facilities • Mental health monitoring • Express writing app development • Chatbox therapy development
Advantages: • Does not require one on one monitoring • Scalable and accessible • Real-time feedback • Can help overcome anxiety in one-on-one sessions • User autonomy
Development-To-Date: Software has been successfully demonstrated in an exploratory study with numerous participants and mental health professionals.
Reference: UCLA Case No. 2023-084
Lead Inventor: Xiang Anthony Chen