×
A System for Storing Journal Entries and Implementing Psychotherapy using LLMs And Support Vector Machines

Authors

Zhijun Zhang1, Austin Amakye Ansah2 and Ang Li3, 1Columbia International College, Canada, 2The University of Texas at Arlington, USA, 3California State Polytechnic University, USA

Abstract

Some people keep journals to track their mental health or keep a record of things happening in their lives [9]. While journaling can help identify patterns in mood and tackle stress and anxiety at the root cause, only 8 percent of the population do it. With the 8.58 billion mobile subscriptions in use worldwide, we take advantage of mobile applications to deliver a quick on-the-go solution for mobile journaling that can be used free of charge [10]. This application utilizes NLP to determine user mood and provide tasks and goals that the user can work towards to improve their well-being. The NLP model developed in this paper has an accuracy of about 91% in correctly classifying moods on a sequence of words in a validation dataset. The model is good enough for most text-based emotional sentiment analysis needs but could be re-trained to attain better results.

Keywords
Journal, AI, Mental Health, Chat