東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

A Hybrid Structured-Neural Dialog System for Automated Counseling.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A Hybrid Structured-Neural Dialog System for Automated Counseling./
作者:	Olafsson, Stefan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	136 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28651896
ISBN:	9798535512327

A Hybrid Structured-Neural Dialog System for Automated Counseling.
Olafsson, Stefan.

A Hybrid Structured-Neural Dialog System for Automated Counseling. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 136 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Northeastern University, 2021.

This item is not available from ProQuest Dissertations & Theses.

Many therapeutic counseling techniques require the counselor to provide appropriate responses to open-ended client talk. Contemporary approaches to automated counseling either constrain user input or respond using simple rule-based methods, leading to less personalized responses and inflexible conversation. In this work I explore the use of a hybrid dialogue management approach that combines the use of rule-based sequencing through a predefined counselor-driven therapeutic agenda with neural network-based natural language processing to respond to individual client utterances, allowing for automated responses to unconstrained client speech in well-circumscribed discourse contexts. This architecture was implemented in an automated counselor that uses techniques from cognitive behavioral therapy (CBT) and motivational interviewing (MI) to help individuals with mild to moderate alcohol use disorder decrease their alcohol consumption. CBT and MI are effective client-centered counseling method for motivating people to change. Unfortunately, many people avoid therapy, citing barriers that could be addressed by automated counselors that simulate face-to-face counseling, such as lack of time, feeling stigmatized, and financial constraints. However, key counseling techniques, such as reflective listening in MI, require making appropriate responses to unconstrained client speech. I report the development and evaluation of a virtual agent counseling system that conducts CBT-MI sessions with college students with mild to moderate Alcohol Use Disorder. I conducted a feasibility study assessing the acceptance of a prototype virtual agent counselor among patients with substance use disorder, developed data-driven models that predict counseling behaviors and models that generate the language for counselor reflections trained from transcripts of counseling sessions using neural networks. Finally, I built a virtual counseling system that uses the hybrid structured-neural dialog manager and conducted a randomized experiment evaluating the virtual agent counseling system efficacy conducting CBT-MI sessions with college students facing alcohol use problems. After one session with the virtual counselor, there was an increase in participants' readiness, confidence, motivation, and commitment to changing their drinking habits.

ISBN: 9798535512327Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Counseling psychology

A Hybrid Structured-Neural Dialog System for Automated Counseling.
LDR:03629nmm a2200397 4500 001 2346462
005 20230315102217.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798535512327
035 $a (MiAaPQ)AAI28651896
035 $a AAI28651896
040 $a MiAaPQ $c MiAaPQ
100 1 $a Olafsson, Stefan. $3 3685562
245 1 0 $a A Hybrid Structured-Neural Dialog System for Automated Counseling.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 136 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Bickmore, Timothy.
502 $a Thesis (Ph.D.)--Northeastern University, 2021.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be sold to any third party vendors.
520 $a Many therapeutic counseling techniques require the counselor to provide appropriate responses to open-ended client talk. Contemporary approaches to automated counseling either constrain user input or respond using simple rule-based methods, leading to less personalized responses and inflexible conversation. In this work I explore the use of a hybrid dialogue management approach that combines the use of rule-based sequencing through a predefined counselor-driven therapeutic agenda with neural network-based natural language processing to respond to individual client utterances, allowing for automated responses to unconstrained client speech in well-circumscribed discourse contexts. This architecture was implemented in an automated counselor that uses techniques from cognitive behavioral therapy (CBT) and motivational interviewing (MI) to help individuals with mild to moderate alcohol use disorder decrease their alcohol consumption. CBT and MI are effective client-centered counseling method for motivating people to change. Unfortunately, many people avoid therapy, citing barriers that could be addressed by automated counselors that simulate face-to-face counseling, such as lack of time, feeling stigmatized, and financial constraints. However, key counseling techniques, such as reflective listening in MI, require making appropriate responses to unconstrained client speech. I report the development and evaluation of a virtual agent counseling system that conducts CBT-MI sessions with college students with mild to moderate Alcohol Use Disorder. I conducted a feasibility study assessing the acceptance of a prototype virtual agent counselor among patients with substance use disorder, developed data-driven models that predict counseling behaviors and models that generate the language for counselor reflections trained from transcripts of counseling sessions using neural networks. Finally, I built a virtual counseling system that uses the hybrid structured-neural dialog manager and conducted a randomized experiment evaluating the virtual agent counseling system efficacy conducting CBT-MI sessions with college students facing alcohol use problems. After one session with the virtual counselor, there was an increase in participants' readiness, confidence, motivation, and commitment to changing their drinking habits.
590 $a School code: 0160.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Counseling psychology. $3 924824
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Collaboration. $3 3556296
650 4 $a Addictive behaviors. $3 3563047
650 4 $a Intervention. $3 3435307
653 $a Counseling psychology
653 $a Human-computer Interaction
653 $a Natural language processing
653 $a Virtual agents
690 $a 0984
690 $a 0800
690 $a 0603
710 2 $a Northeastern University. $b Computer Science. $3 1678818
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0160
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28651896