Cognitive Emotional Embedded Representations of Text to Predict Suicidal Ideation and Psychiatric Symptoms

Mauricio Toledo-Acosta,Maria Luisa Barrigon,Asela Reig-Alamillo,Enrique Baca-Garcia,Jorge Hermosillo-Valadez,Fuensanta Aroca Bisquert,Markus Müller,Talin Barreiro

doi:10.3390/math8112088

Mauricio Toledo-Acosta, Maria Luisa Barrigon + Show 6 more

Open Access

https://doi.org/10.3390/math8112088

Copy DOI

Abstract

Mathematical modeling of language in Artificial Intelligence is of the utmost importance for many research areas and technological applications. Over the last decade, research on text representation has been directed towards the investigation of dense vectors popularly known as word embeddings. In this paper, we propose a cognitive-emotional scoring and representation framework for text based on word embeddings. This representation framework aims to mathematically model the emotional content of words in short free-form text messages, produced by adults in follow-up due to any mental health condition in the outpatient facilities within the Psychiatry Department of Hospital Fundación Jiménez Díaz in Madrid, Spain. Our contribution is a geometrical-topological framework for Sentiment Analysis, that includes a hybrid method that uses a cognitively-based lexicon together with word embeddings to generate graded sentiment scores for words, and a new topological method for clustering dense vector representations in high-dimensional spaces, where points are very sparsely distributed. Our framework is useful in detecting word association topics, emotional scoring patterns, and embedded vectors’ geometrical behavior, which might be useful in understanding language use in this kind of texts. Our proposed scoring system and representation framework might be helpful in studying relations between language and behavior and their use might have a predictive potential to prevent suicide.

Highlights

Suicide is a major public health concern in modern society as it is one of the leading causes of death worldwide [1]
Our contribution is a geometrical-topological framework for Sentiment Analysis, that includes a hybrid method that uses a cognitively-based lexicon together with word embeddings to generate graded sentiment scores for words, and a new topological method for clustering dense vector representations in high-dimensional spaces
Helping to prevent suicide is the major motivation of our work

Summary

Introduction

Suicide is a major public health concern in modern society as it is one of the leading causes of death worldwide [1]. Researchers from many areas worldwide have dedicated great effort to preventing suicide [2]. Our approach is to mathematically represent and analyze the linguistic patterns of texts written by subjects under psychiatric treatment who tend to express death wishes. Language Processing (NLP) based on semantic text similarity methods has been applied to this and other similar tasks such as Sentiment Analysis [3,4]. One of the most effective methods used in NLP consists in computing dense vector representations of words by means of neural networks. A telling example is the acclaimed word2vec model [5]

Objectives

Results

Discussion

Conclusion