Cargando…

An optimized deep learning approach for suicide detection through Arabic tweets

Many people worldwide suffer from mental illnesses such as major depressive disorder (MDD), which affect their thoughts, behavior, and quality of life. Suicide is regarded as the second leading cause of death among teenagers when treatment is not received. Twitter is a platform for expressing their...

Descripción completa

Detalles Bibliográficos
Autores principales: Baghdadi, Nadiah A., Malki, Amer, Magdy Balaha, Hossam, AbdulAzeem, Yousry, Badawy, Mahmoud, Elhosseini, Mostafa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455273/
https://www.ncbi.nlm.nih.gov/pubmed/36092010
http://dx.doi.org/10.7717/peerj-cs.1070
_version_ 1784785546471538688
author Baghdadi, Nadiah A.
Malki, Amer
Magdy Balaha, Hossam
AbdulAzeem, Yousry
Badawy, Mahmoud
Elhosseini, Mostafa
author_facet Baghdadi, Nadiah A.
Malki, Amer
Magdy Balaha, Hossam
AbdulAzeem, Yousry
Badawy, Mahmoud
Elhosseini, Mostafa
author_sort Baghdadi, Nadiah A.
collection PubMed
description Many people worldwide suffer from mental illnesses such as major depressive disorder (MDD), which affect their thoughts, behavior, and quality of life. Suicide is regarded as the second leading cause of death among teenagers when treatment is not received. Twitter is a platform for expressing their emotions and thoughts about many subjects. Many studies, including this one, suggest using social media data to track depression and other mental illnesses. Even though Arabic is widely spoken and has a complex syntax, depressive detection methods have not been applied to the language. The Arabic tweets dataset should be scraped and annotated first. Then, a complete framework for categorizing tweet inputs into two classes (such as Normal or Suicide) is suggested in this study. The article also proposes an Arabic tweet preprocessing algorithm that contrasts lemmatization, stemming, and various lexical analysis methods. Experiments are conducted using Twitter data scraped from the Internet. Five different annotators have annotated the data. Performance metrics are reported on the suggested dataset using the latest Bidirectional Encoder Representations from Transformers (BERT) and Universal Sentence Encoder (USE) models. The measured performance metrics are balanced accuracy, specificity, F1-score, IoU, ROC, Youden Index, NPV, and weighted sum metric (WSM). Regarding USE models, the best-weighted sum metric (WSM) is 80.2%, and with regards to Arabic BERT models, the best WSM is 95.26%.
format Online
Article
Text
id pubmed-9455273
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-94552732022-09-09 An optimized deep learning approach for suicide detection through Arabic tweets Baghdadi, Nadiah A. Malki, Amer Magdy Balaha, Hossam AbdulAzeem, Yousry Badawy, Mahmoud Elhosseini, Mostafa PeerJ Comput Sci Computational Linguistics Many people worldwide suffer from mental illnesses such as major depressive disorder (MDD), which affect their thoughts, behavior, and quality of life. Suicide is regarded as the second leading cause of death among teenagers when treatment is not received. Twitter is a platform for expressing their emotions and thoughts about many subjects. Many studies, including this one, suggest using social media data to track depression and other mental illnesses. Even though Arabic is widely spoken and has a complex syntax, depressive detection methods have not been applied to the language. The Arabic tweets dataset should be scraped and annotated first. Then, a complete framework for categorizing tweet inputs into two classes (such as Normal or Suicide) is suggested in this study. The article also proposes an Arabic tweet preprocessing algorithm that contrasts lemmatization, stemming, and various lexical analysis methods. Experiments are conducted using Twitter data scraped from the Internet. Five different annotators have annotated the data. Performance metrics are reported on the suggested dataset using the latest Bidirectional Encoder Representations from Transformers (BERT) and Universal Sentence Encoder (USE) models. The measured performance metrics are balanced accuracy, specificity, F1-score, IoU, ROC, Youden Index, NPV, and weighted sum metric (WSM). Regarding USE models, the best-weighted sum metric (WSM) is 80.2%, and with regards to Arabic BERT models, the best WSM is 95.26%. PeerJ Inc. 2022-08-23 /pmc/articles/PMC9455273/ /pubmed/36092010 http://dx.doi.org/10.7717/peerj-cs.1070 Text en © 2022 Baghdadi et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Computational Linguistics
Baghdadi, Nadiah A.
Malki, Amer
Magdy Balaha, Hossam
AbdulAzeem, Yousry
Badawy, Mahmoud
Elhosseini, Mostafa
An optimized deep learning approach for suicide detection through Arabic tweets
title An optimized deep learning approach for suicide detection through Arabic tweets
title_full An optimized deep learning approach for suicide detection through Arabic tweets
title_fullStr An optimized deep learning approach for suicide detection through Arabic tweets
title_full_unstemmed An optimized deep learning approach for suicide detection through Arabic tweets
title_short An optimized deep learning approach for suicide detection through Arabic tweets
title_sort optimized deep learning approach for suicide detection through arabic tweets
topic Computational Linguistics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455273/
https://www.ncbi.nlm.nih.gov/pubmed/36092010
http://dx.doi.org/10.7717/peerj-cs.1070
work_keys_str_mv AT baghdadinadiaha anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT malkiamer anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT magdybalahahossam anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT abdulazeemyousry anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT badawymahmoud anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT elhosseinimostafa anoptimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT baghdadinadiaha optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT malkiamer optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT magdybalahahossam optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT abdulazeemyousry optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT badawymahmoud optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets
AT elhosseinimostafa optimizeddeeplearningapproachforsuicidedetectionthrougharabictweets