Towards AI-driven and Emotion-adaptive Mental Health Platform to Enhance Therapeutic Processes

Nowadays, mental health issues have become a major public health challenge. Moodie app allows patients to track their emotions, moods, routines, sleep, diet, physical activity, and associated context via journal logs. This provides the therapist with a rich pool of data for accurate diagnosis and assists with the treatment. This project aims to (1) Develop machine learning models and evaluate their ability to predict individual’s emotional state using over one year journaling log and associated emotion from Moodie app. (2) Compare the performance of different machine learning models to determine the best performing model for predicting emotions from tracked data. (3) Using a combination machine learning and thematic analysis identify both the negative and positive factors that affect people’s mood. (4) Evaluate the User Experience (UX) and Usability of the app. This is the first step toward developing a user-friendly AI-adaptive and emotion-driven mental health intervention

Faculty Supervisor:

Rita Orji

Student:

Partner:

Moodie Inc

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Dalhousie University

Program: