Deep Learning Mental Health Dialogue System

Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial intelligence (AI) models designed for mental health counseling could help improve outcomes by lowering barriers to access. To this end, we have deve...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Conference on Big Data and Smart Computing s. 395 - 398
Hlavní autoři: Brocki, Lennart, Dyer, George C., Gladka, Anna, Chung, Neo Christopher
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.02.2023
Témata:
ISSN:2375-9356
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial intelligence (AI) models designed for mental health counseling could help improve outcomes by lowering barriers to access. To this end, we have developed a deep learning (DL) dialogue system called Serena. The system consists of a core generative model and post-processing algorithms. The core generative model is a 2.7 billion parameter Seq2Seq Transformer [26] fine-tuned on thousands of transcripts of person-centered-therapy (PCT) sessions. The series of postprocessing algorithms detects contradictions, improves coherency, and removes repetitive answers. Serena is implemented and deployed on https://serena.chat, which currently offers limited free services. While the dialogue system is capable of responding in a qualitatively empathetic and engaging manner, occasionally it displays hallucination and long-term incoherence. Overall, we demonstrate that a deep learning mental health dialogue system has the potential to provide a low-cost and effective complement to traditional human counselors with less barriers to access.
AbstractList Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial intelligence (AI) models designed for mental health counseling could help improve outcomes by lowering barriers to access. To this end, we have developed a deep learning (DL) dialogue system called Serena. The system consists of a core generative model and post-processing algorithms. The core generative model is a 2.7 billion parameter Seq2Seq Transformer [26] fine-tuned on thousands of transcripts of person-centered-therapy (PCT) sessions. The series of postprocessing algorithms detects contradictions, improves coherency, and removes repetitive answers. Serena is implemented and deployed on https://serena.chat, which currently offers limited free services. While the dialogue system is capable of responding in a qualitatively empathetic and engaging manner, occasionally it displays hallucination and long-term incoherence. Overall, we demonstrate that a deep learning mental health dialogue system has the potential to provide a low-cost and effective complement to traditional human counselors with less barriers to access.
Author Dyer, George C.
Gladka, Anna
Chung, Neo Christopher
Brocki, Lennart
Author_xml – sequence: 1
  givenname: Lennart
  surname: Brocki
  fullname: Brocki, Lennart
  email: brocki.lennart@gmail.com
  organization: Institute of Informatics University of Warsaw,Warsaw,Poland
– sequence: 2
  givenname: George C.
  surname: Dyer
  fullname: Dyer, George C.
  email: georgecdyer@gmail.com
  organization: Demiteris,Wrocław,Poland
– sequence: 3
  givenname: Anna
  surname: Gladka
  fullname: Gladka, Anna
  email: agladka@gmail.com
  organization: Wrocław Medical University,Psychiatry Department,Wrocław,Poland
– sequence: 4
  givenname: Neo Christopher
  surname: Chung
  fullname: Chung, Neo Christopher
  email: nchchung@gmail.com
  organization: Institute of Informatics University of Warsaw,Warsaw,Poland
BookMark eNotjMtKw0AUQEdRsNb8gWD2knjnPXepqVoh4kJdl4lzE0fyIomL_n0LujpwOJxLdtYPPTF2wyHnHPDuITbF0I3aCqlyAULmAID2hCVoHTdGK6ut06dsJaTVGUptLlgyzz_HjKNBYWHFbjdEY1qSn_rYN-kr9Ytv0y35dvlON9G3Q_NL6ft-Xqi7Yue1b2dK_rlmn0-PH8U2K9-eX4r7MosC1JJxwQUGCJV2WHMJJnj95bwgHiplOHlCcAFBVNJ5fXSVIQx1ACuUlirINbv--0Yi2o1T7Py033EAY6wCeQBlbEXg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BigComp57234.2023.00097
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9781665475785
1665475781
EISSN 2375-9356
EndPage 398
ExternalDocumentID 10066740
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i204t-12129d0db589f1306da5c8a2e1db461eae908d902b38a5db4b6e9dfd0724534d3
IEDL.DBID RIE
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000981866800088&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:52:23 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-12129d0db589f1306da5c8a2e1db461eae908d902b38a5db4b6e9dfd0724534d3
PageCount 4
ParticipantIDs ieee_primary_10066740
PublicationCentury 2000
PublicationDate 2023-Feb.
PublicationDateYYYYMMDD 2023-02-01
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-Feb.
PublicationDecade 2020
PublicationTitle International Conference on Big Data and Smart Computing
PublicationTitleAbbrev BIGCOMP
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001969270
Score 1.955146
Snippet Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial...
SourceID ieee
SourceType Publisher
StartPage 395
SubjectTerms Artificial Intelligence
Big Data
Chatbot
Costs
Deep learning
Dialogue System
Employee welfare
Mental health
Transformer cores
Transformers
Title Deep Learning Mental Health Dialogue System
URI https://ieeexplore.ieee.org/document/10066740
WOSCitedRecordID wos000981866800088&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED1BxcBUPoL4lgfWgOM4sb3yUTGgqgNI3SonvlRZ0qq0_H7OdkpZGNgsD5ad6Pz0zvfeAdwh1sZaztOmNlUqbdmkFhviPFZYYs-WOHTwmX1T47GeTs2kF6sHLQwihuIzvPfD8JbvFvXGp8oown1JpiSGvq-UimKtXULFlEYo3tdwZdw8PLZzH1SFErnPngjvZRrcnX71UQkwMhr-cwNHkOwEeWzyAzXHsIfdCQy3HRlYH6CnQNcHLlnvmTpn0aCHRakRe25jooZFl_IEPkYv70-vad8OIW0Fl-s0I5Qxjruq0KYh6CmdLWptBWaukmWGFg3XznBR5doWNFeVaFzjuBKyyKXLz2DQLTo8B1ZrkTcGCcAq7-jFraQwJGrmNC1ScH4BiT_8bBkdL2bbc1_-MX8Fh_77xmrmaxisVxu8gYP6a91-rm7Df_oGcS2SnQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6hggRTeQTxxgNrwHHsxF55VEWUqkORulVOfKmypFVp-f34kVIWBjbLg2UnOn_6zvd9B3CHWCqtKY2rUhUx11kVa6ws59FMW_asLYf2PrODfDiUk4katWJ1r4VBRF98hvdu6N_yzbxcu1SZjXBXksktQ98VnLMkyLW2KRWVKZbTtooroerhsZ65sBI5S13-hDk3U-_v9KuTigeSXvefWziEaCvJI6MfsDmCHWyOobvpyUDaED0Be4HggrSuqTMSLHpIEBuR5zqkakjwKY_go_cyfurHbUOEuGaUr-LE4owy1BRCqsqCT2a0KKVmmJiCZwlqVFQaRVmRSi3sXJGhMpWhOeMi5SY9hU4zb_AMSClZWim0EFY4Ty-quQ1ES86MtIsISs8hcoefLoLnxXRz7os_5m9hvz9-H0wHr8O3Szhw3zrUNl9BZ7Vc4zXslV-r-nN54__ZN0chleQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=International+Conference+on+Big+Data+and+Smart+Computing&rft.atitle=Deep+Learning+Mental+Health+Dialogue+System&rft.au=Brocki%2C+Lennart&rft.au=Dyer%2C+George+C.&rft.au=Gladka%2C+Anna&rft.au=Chung%2C+Neo+Christopher&rft.date=2023-02-01&rft.pub=IEEE&rft.eissn=2375-9356&rft.spage=395&rft.epage=398&rft_id=info:doi/10.1109%2FBigComp57234.2023.00097&rft.externalDocID=10066740