Using Artificial Intelligence to Aid Depression Detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRN |
Texto Completo: | https://repositorio.ufrn.br/handle/123456789/43663 |
Resumo: | Depression is a mental illness that affects a person’s mood, thinking, and behavior. Besides personal distress, depression is also considered a matter of public health. Recent research shows the advantages of using machine learning algorithms to automate and improve the screening for depression. In this thesis, we address the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) database, comprising clinical interviews and questionnaire assessments of over a hundred individuals. To automate the screening, we investigate a deep learning multimodal model, combining audio, visual, and text features. These features are extracted using VGGish model, OpenFace, and Doc2Vec, respectively, and fed into a multilayer perceptron (MLP) network to classify individuals as depressed or non-depressed. We compare the proposed approach to similar existing approaches from the literature through standard binary classification metrics. |
id |
UFRN_8a61c469a23eddaf5734f940c6e80ab2 |
---|---|
oai_identifier_str |
oai:https://repositorio.ufrn.br:123456789/43663 |
network_acronym_str |
UFRN |
network_name_str |
Repositório Institucional da UFRN |
repository_id_str |
|
spelling |
Neves, Deângela Caroline GomesAranha, Claus de Castrode Araújo, Daniel Sabino AmorimBezerra, Leonardo César TeonácioBezerra, Leonardo César Teonácio2019-07-16T13:52:11Z2021-10-06T11:52:26Z2019-07-16T13:52:11Z2021-10-06T11:52:26Z2019-06-2620170155372NEVES. Deângela Caroline Gomes. Using Artificial Intelligence to Aid Depression Detection. 2019. 25f. Trabalho de Conclusão de Curso (Graduação em Engenharia da Computação) - Departamento de Engenharia da Computação, Universidade Federal do Rio Grande do Norte, Natal, 2019.https://repositorio.ufrn.br/handle/123456789/43663Depression is a mental illness that affects a person’s mood, thinking, and behavior. Besides personal distress, depression is also considered a matter of public health. Recent research shows the advantages of using machine learning algorithms to automate and improve the screening for depression. In this thesis, we address the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) database, comprising clinical interviews and questionnaire assessments of over a hundred individuals. To automate the screening, we investigate a deep learning multimodal model, combining audio, visual, and text features. These features are extracted using VGGish model, OpenFace, and Doc2Vec, respectively, and fed into a multilayer perceptron (MLP) network to classify individuals as depressed or non-depressed. We compare the proposed approach to similar existing approaches from the literature through standard binary classification metrics.A depressão é um transtorno psicológico que causa alterações comportamentais e no humor de uma pessoa, e é considerada um problema de saúde pública. Estudos recentes mostram as vantagens de se utilizar algoritmos de machine learning não só para automatizar, mas também melhorar o processo de triagem para depressão. Neste trabalho, é feito uma análise de dados exploratória no dataset Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ), que consiste em um conjunto entrevistas clínicas e questionários de mais de 100 indivíduos. Além disso, utiliza-se a mesma base de dados para desenvolver um modelo multimodal de Aprendizagem Profunda, que combina dados de áudio, vídeo e texto para classificar o resultado de triagens para depressão. Os dados utilizados no modelo são extraídos a partir de uma rede pretreinada VGGish, do OpenFace e Doc2Vec, respectivamente. Em seguida, esses dados são utilizados para alimentar uma rede neural perceptron de múltiplas camadas, que os classifica como depressivos ou não-depressivos na triagem. Por fim, o modelo proposto é comparado a outras abordagens existentes na literatura a partir de metricas padrão de classificação binária.Universidade Federal do Rio Grande do NorteUFRNBrasilEngenharia da ComputaçãoDeep LearningDepressionDAIC-WOZUsing Artificial Intelligence to Aid Depression Detectioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesisengreponame:Repositório Institucional da UFRNinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNinfo:eu-repo/semantics/openAccessORIGINALUsingArtifical_Neves_2019.pdfapplication/pdf3958493https://repositorio.ufrn.br/bitstream/123456789/43663/1/UsingArtifical_Neves_2019.pdf7329b9dee4ab075edffc574b59083ec3MD51CC-LICENSElicense_rdfapplication/octet-stream701https://repositorio.ufrn.br/bitstream/123456789/43663/2/license_rdf42fd4ad1e89814f5e4a476b409eb708cMD52LICENSElicense.txttext/plain714https://repositorio.ufrn.br/bitstream/123456789/43663/3/license.txt7278bab9c5c886812fa7d225dc807888MD53TEXTUsingArtifical_Neves_2019.pdf.txtExtracted texttext/plain43351https://repositorio.ufrn.br/bitstream/123456789/43663/4/UsingArtifical_Neves_2019.pdf.txt892cd1a311fb402b57e05fe286ecba7cMD54123456789/436632023-03-09 19:25:04.973oai:https://repositorio.ufrn.br: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ório de PublicaçõesPUBhttp://repositorio.ufrn.br/oai/opendoar:2023-03-09T22:25:04Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)false |
dc.title.pt_BR.fl_str_mv |
Using Artificial Intelligence to Aid Depression Detection |
title |
Using Artificial Intelligence to Aid Depression Detection |
spellingShingle |
Using Artificial Intelligence to Aid Depression Detection Neves, Deângela Caroline Gomes Deep Learning Depression DAIC-WOZ |
title_short |
Using Artificial Intelligence to Aid Depression Detection |
title_full |
Using Artificial Intelligence to Aid Depression Detection |
title_fullStr |
Using Artificial Intelligence to Aid Depression Detection |
title_full_unstemmed |
Using Artificial Intelligence to Aid Depression Detection |
title_sort |
Using Artificial Intelligence to Aid Depression Detection |
author |
Neves, Deângela Caroline Gomes |
author_facet |
Neves, Deângela Caroline Gomes |
author_role |
author |
dc.contributor.referees1.none.fl_str_mv |
Aranha, Claus de Castro |
dc.contributor.referees2.none.fl_str_mv |
de Araújo, Daniel Sabino Amorim |
dc.contributor.referees3.none.fl_str_mv |
Bezerra, Leonardo César Teonácio |
dc.contributor.author.fl_str_mv |
Neves, Deângela Caroline Gomes |
dc.contributor.advisor1.fl_str_mv |
Bezerra, Leonardo César Teonácio |
contributor_str_mv |
Bezerra, Leonardo César Teonácio |
dc.subject.por.fl_str_mv |
Deep Learning Depression DAIC-WOZ |
topic |
Deep Learning Depression DAIC-WOZ |
description |
Depression is a mental illness that affects a person’s mood, thinking, and behavior. Besides personal distress, depression is also considered a matter of public health. Recent research shows the advantages of using machine learning algorithms to automate and improve the screening for depression. In this thesis, we address the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) database, comprising clinical interviews and questionnaire assessments of over a hundred individuals. To automate the screening, we investigate a deep learning multimodal model, combining audio, visual, and text features. These features are extracted using VGGish model, OpenFace, and Doc2Vec, respectively, and fed into a multilayer perceptron (MLP) network to classify individuals as depressed or non-depressed. We compare the proposed approach to similar existing approaches from the literature through standard binary classification metrics. |
publishDate |
2019 |
dc.date.accessioned.fl_str_mv |
2019-07-16T13:52:11Z 2021-10-06T11:52:26Z |
dc.date.available.fl_str_mv |
2019-07-16T13:52:11Z 2021-10-06T11:52:26Z |
dc.date.issued.fl_str_mv |
2019-06-26 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.pt_BR.fl_str_mv |
20170155372 |
dc.identifier.citation.fl_str_mv |
NEVES. Deângela Caroline Gomes. Using Artificial Intelligence to Aid Depression Detection. 2019. 25f. Trabalho de Conclusão de Curso (Graduação em Engenharia da Computação) - Departamento de Engenharia da Computação, Universidade Federal do Rio Grande do Norte, Natal, 2019. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufrn.br/handle/123456789/43663 |
identifier_str_mv |
20170155372 NEVES. Deângela Caroline Gomes. Using Artificial Intelligence to Aid Depression Detection. 2019. 25f. Trabalho de Conclusão de Curso (Graduação em Engenharia da Computação) - Departamento de Engenharia da Computação, Universidade Federal do Rio Grande do Norte, Natal, 2019. |
url |
https://repositorio.ufrn.br/handle/123456789/43663 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal do Rio Grande do Norte |
dc.publisher.initials.fl_str_mv |
UFRN |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Engenharia da Computação |
publisher.none.fl_str_mv |
Universidade Federal do Rio Grande do Norte |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRN instname:Universidade Federal do Rio Grande do Norte (UFRN) instacron:UFRN |
instname_str |
Universidade Federal do Rio Grande do Norte (UFRN) |
instacron_str |
UFRN |
institution |
UFRN |
reponame_str |
Repositório Institucional da UFRN |
collection |
Repositório Institucional da UFRN |
bitstream.url.fl_str_mv |
https://repositorio.ufrn.br/bitstream/123456789/43663/1/UsingArtifical_Neves_2019.pdf https://repositorio.ufrn.br/bitstream/123456789/43663/2/license_rdf https://repositorio.ufrn.br/bitstream/123456789/43663/3/license.txt https://repositorio.ufrn.br/bitstream/123456789/43663/4/UsingArtifical_Neves_2019.pdf.txt |
bitstream.checksum.fl_str_mv |
7329b9dee4ab075edffc574b59083ec3 42fd4ad1e89814f5e4a476b409eb708c 7278bab9c5c886812fa7d225dc807888 892cd1a311fb402b57e05fe286ecba7c |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN) |
repository.mail.fl_str_mv |
|
_version_ |
1802117641054191616 |