Automatic Psychological Text Analysis using Recurrent Neural Networks

Abstract

Schema therapy is a type of psychological treatment for people suffering from personality disorders. A schema is a core psychological state of mind that influences external behaviour through the development of coping styles. Current schema therapy is time inefficient and human-processed. Enabling automatic schema classification helps the overall goal of creating a chatbot that can classify schema modes from conversations. The goal of this research was to optimize a Recurrent Neural Network (RNN) model to classify patient’s schema modes from a dataset containing a recent emotional story from participants and are labeled with SMI questionnaire answers. Three RNN models were created: a binary classification Multilabel RNN, a binary classification Per-Schema RNN and a ordinal classification Per-Schema RNN. The results have shown that the binary classification Multilabel model scores an average F1-score of 0.48. The binary classification Per-Schema model scores an average F1-score of 0.49. While ordinal classification Per-Schema model performs with an average Spearman Coefficient of 0.15.