EMPLOYING LONG SHORT-TERM MEMORY NETWORKS IN TRIGGER DETECTION FOR EMETOPHOBIA

Abstract

Research focused on mental health-related issues is vital to the modern person’s life. Specific phobias are part of the anxiety disorder umbrella and they are distressing afflictions. Emetophobia is the rarely known, yet fairly common and highly disruptive specific phobia of vomiting. Unlike other phobias, emetophobia is triggered not only by the object of the specific fear, but also by verbal and written mentions of said object. This paper proposes and compares ten neural network-based architectures that discern between triggering and non-triggering groups of written words. An interface is created, where the best models can be used in emetophobia related applications. This interface is then integrated into an application that can be used by emetophobes to censor online content such that the exposure to triggers is controlled, patient-centered, and patient-paced.

Keywords

• machine learning, text classification, long short-term memory, trigger detection, natural language processing, neural networks.