Citation: Diniz, E.; Fontenele, J.E.; de
Oliveira, A.C.; Bastos, V.H.; Teixeira,
S.; Rabêlo, R.; Calçada, D.B.; dos
Santos, R.; de Oliveira, A.K.; Teles,
A.S. Boamente: A Natural Language
Processing-Based Digital
Phenotyping Tool for Smart
Monitoring of Suicidal Ideation.
Healthcare 2022, 10, 698. https://
doi.org/10.3390/healthcare10040698
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 1 February 2022
Accepted: 5 April 2022
Published: 8 April 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Boamente: A Natural Language Processing-Based Digital
Phenotyping Tool for Smart Monitoring of Suicidal Ideation
Evandro J. S. Diniz
1,2
, José E. Fontenele
2
, Adonias C. de Oliveira
2
, Victor H. Bastos
2
, Silmar Teixeira
2
,
Ricardo L. Rabêlo
3
, Dario B. Calçada
4
, Renato M. dos Santos
2,3
, Ana K. de Oliveira
3
and Ariel S. Teles
1,2,∗
1
Federal Institute of Maranhão, Araioses 65570-000, Brazil; evandro.diniz@ifma.edu.br
2
Technological Neuro Innovation Laboratory, Federal University of Delta do Parnaíba,
Parnaíba 64202-020, Brazil; vetophp@gmail.com (J.E.F.); adonias.ifce@gmail.com (A.C.d.O.);
victorhugobastos@ufpi.edu.br (V.H.B.); silmarteixeira@ufpi.edu.br (S.T.);
renatomendes@ufpi.edu.br (R.M.d.S.)
3
Department of Electrical Engineering, Federal University of Piauí, Teresina 64049-550, Brazil;
ricardoalr@ufpi.edu.br (R.L.R.); anakarla_deoliveira@yahoo.com.br (A.K.d.O.)
4
Department of Computer Science, State University of Piauí, Parnaíba 64202-220, Brazil;
dariobcalcada@frn.uespi.br
* Correspondence: ariel.teles@ifma.edu.br
Abstract:
People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason,
suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be
monitored in a manner capable of identifying if and when they have a suicidal ideation, enabling
professionals to perform timely interventions. This study aimed to develop the Boamente tool, a
solution that collects textual data from users’ smartphones and identifies the existence of suicidal
ideation. The solution has a virtual keyboard mobile application that passively collects user texts
and sends them to a web platform to be processed. The platform classifies texts using natural
language processing and a deep learning model to recognize suicidal ideation, and the results are
presented to mental health professionals in dashboards. Text classification for sentiment analysis was
implemented with different machine/deep learning algorithms. A validation study was conducted
to identify the model with the best performance results. The BERTimbau Large model performed
better, reaching a recall of 0.953 (accuracy: 0.955; precision: 0.961; F-score: 0.954; AUC: 0.954). The
proposed tool demonstrated an ability to identify suicidal ideation from user texts, which enabled it
to be experimented with in studies with professionals and their patients.
Keywords: artificial intelligence; deep learning; eHealth; mental health; mobile application; natural
language processing; suicide
1. Introduction
1.1. Background
Suicide is one of the main causes of death in the world [
1
]. In 2019, Brazil was
among ten countries where the most suicides occurred in the world, and the second among
countries of the Americas, with 14,540 suicide cases [
2
]. According to the World Health
Organization (WHO), 703,000 people committed suicide in 2019 in the world. As an
aggravating factor, the current COVID-19 pandemic has changed people’s well-being and
mental health due to different events, such as deaths, social isolation, and job closures,
which can also cause an increase in the number of people at risk of suicide [3,4].
Several factors can influence individuals to make the decision to end their lives
(for example, emotional pain, marital problems, and biological, genetic, psychological,
social, cultural, financial, and environmental factors) [5–7]. According to the WHO, when
people are mentally healthy, they are able to be productive, contribute to the community,
Healthcare 2022, 10, 698. https://doi.org/10.3390/healthcare10040698 https://www.mdpi.com/journal/healthcare
