Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis

Masahito Sakishita, Taishiro Kishimoto, Akiho Takinami, Yoko Eguchi, Yoshinobu Kano

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Recently, the number of people who are diagnosed as mental diseases is increasing. Efficient and objective diagnosis is important to start medical treatments in earlier stages. However, mental disease diagnosis is difficult to quantify criteria, because it is performed through conversations with patients, not by physical surveys. We aim to automate mental disease diagnosis in order to resolve these issues. We recorded conversations between psychologists and subjects to build our diagnosis speech corpus. Our subjects include healthy persons, people with mental diseases of depression, bipolar disorder, schizophrenia, anxiety and dementia. All of our subjects are diagnosed by doctors of psychiatry. Then we made accurate transcription manually, adding utterance time stamps, linguistic and non-linguistic annotations. Using our corpus, we performed feature analysis to find characteristics for each disease. We also tried automatic mental disease diagnosis by machine learning, while the number of sample data is few because we were still in our pilot study phase. We will increase the number of subjects in future.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Verlag
Pages111-118
Number of pages8
DOIs
Publication statusPublished - 2020 Jan 1

Publication series

NameStudies in Computational Intelligence
Volume843
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Fingerprint

Transcription
Linguistics
Learning systems
Psychiatry

Keywords

  • Anxiety
  • Bipolar disorder
  • Corpus
  • Dementia
  • Depression
  • Diagnosis
  • Machine learning
  • Mental disease
  • Schizophrenia
  • Utterance

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Sakishita, M., Kishimoto, T., Takinami, A., Eguchi, Y., & Kano, Y. (2020). Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis. In Studies in Computational Intelligence (pp. 111-118). (Studies in Computational Intelligence; Vol. 843). Springer Verlag. https://doi.org/10.1007/978-3-030-24409-5_10

Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis. / Sakishita, Masahito; Kishimoto, Taishiro; Takinami, Akiho; Eguchi, Yoko; Kano, Yoshinobu.

Studies in Computational Intelligence. Springer Verlag, 2020. p. 111-118 (Studies in Computational Intelligence; Vol. 843).

Research output: Chapter in Book/Report/Conference proceedingChapter

Sakishita, M, Kishimoto, T, Takinami, A, Eguchi, Y & Kano, Y 2020, Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis. in Studies in Computational Intelligence. Studies in Computational Intelligence, vol. 843, Springer Verlag, pp. 111-118. https://doi.org/10.1007/978-3-030-24409-5_10
Sakishita M, Kishimoto T, Takinami A, Eguchi Y, Kano Y. Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis. In Studies in Computational Intelligence. Springer Verlag. 2020. p. 111-118. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-030-24409-5_10
Sakishita, Masahito ; Kishimoto, Taishiro ; Takinami, Akiho ; Eguchi, Yoko ; Kano, Yoshinobu. / Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis. Studies in Computational Intelligence. Springer Verlag, 2020. pp. 111-118 (Studies in Computational Intelligence).
@inbook{1cacf3f0bf314dd8a113b5e920af5b69,
title = "Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis",
abstract = "Recently, the number of people who are diagnosed as mental diseases is increasing. Efficient and objective diagnosis is important to start medical treatments in earlier stages. However, mental disease diagnosis is difficult to quantify criteria, because it is performed through conversations with patients, not by physical surveys. We aim to automate mental disease diagnosis in order to resolve these issues. We recorded conversations between psychologists and subjects to build our diagnosis speech corpus. Our subjects include healthy persons, people with mental diseases of depression, bipolar disorder, schizophrenia, anxiety and dementia. All of our subjects are diagnosed by doctors of psychiatry. Then we made accurate transcription manually, adding utterance time stamps, linguistic and non-linguistic annotations. Using our corpus, we performed feature analysis to find characteristics for each disease. We also tried automatic mental disease diagnosis by machine learning, while the number of sample data is few because we were still in our pilot study phase. We will increase the number of subjects in future.",
keywords = "Anxiety, Bipolar disorder, Corpus, Dementia, Depression, Diagnosis, Machine learning, Mental disease, Schizophrenia, Utterance",
author = "Masahito Sakishita and Taishiro Kishimoto and Akiho Takinami and Yoko Eguchi and Yoshinobu Kano",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-24409-5_10",
language = "English",
series = "Studies in Computational Intelligence",
publisher = "Springer Verlag",
pages = "111--118",
booktitle = "Studies in Computational Intelligence",
address = "Germany",

}

TY - CHAP

T1 - Large-Scale Dialog Corpus Towards Automatic Mental Disease Diagnosis

AU - Sakishita, Masahito

AU - Kishimoto, Taishiro

AU - Takinami, Akiho

AU - Eguchi, Yoko

AU - Kano, Yoshinobu

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Recently, the number of people who are diagnosed as mental diseases is increasing. Efficient and objective diagnosis is important to start medical treatments in earlier stages. However, mental disease diagnosis is difficult to quantify criteria, because it is performed through conversations with patients, not by physical surveys. We aim to automate mental disease diagnosis in order to resolve these issues. We recorded conversations between psychologists and subjects to build our diagnosis speech corpus. Our subjects include healthy persons, people with mental diseases of depression, bipolar disorder, schizophrenia, anxiety and dementia. All of our subjects are diagnosed by doctors of psychiatry. Then we made accurate transcription manually, adding utterance time stamps, linguistic and non-linguistic annotations. Using our corpus, we performed feature analysis to find characteristics for each disease. We also tried automatic mental disease diagnosis by machine learning, while the number of sample data is few because we were still in our pilot study phase. We will increase the number of subjects in future.

AB - Recently, the number of people who are diagnosed as mental diseases is increasing. Efficient and objective diagnosis is important to start medical treatments in earlier stages. However, mental disease diagnosis is difficult to quantify criteria, because it is performed through conversations with patients, not by physical surveys. We aim to automate mental disease diagnosis in order to resolve these issues. We recorded conversations between psychologists and subjects to build our diagnosis speech corpus. Our subjects include healthy persons, people with mental diseases of depression, bipolar disorder, schizophrenia, anxiety and dementia. All of our subjects are diagnosed by doctors of psychiatry. Then we made accurate transcription manually, adding utterance time stamps, linguistic and non-linguistic annotations. Using our corpus, we performed feature analysis to find characteristics for each disease. We also tried automatic mental disease diagnosis by machine learning, while the number of sample data is few because we were still in our pilot study phase. We will increase the number of subjects in future.

KW - Anxiety

KW - Bipolar disorder

KW - Corpus

KW - Dementia

KW - Depression

KW - Diagnosis

KW - Machine learning

KW - Mental disease

KW - Schizophrenia

KW - Utterance

UR - http://www.scopus.com/inward/record.url?scp=85070566443&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070566443&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-24409-5_10

DO - 10.1007/978-3-030-24409-5_10

M3 - Chapter

AN - SCOPUS:85070566443

T3 - Studies in Computational Intelligence

SP - 111

EP - 118

BT - Studies in Computational Intelligence

PB - Springer Verlag

ER -