Academic Journal
View in EDS

Two Heads May Be Better than One: Learning from Computer Agents in Conversational Trialogues

Bibliographic Details
Title: Two Heads May Be Better than One: Learning from Computer Agents in Conversational Trialogues
Language: English
Authors: Graesser, Arthur C., Forsyth, Carol M., Lehman, Blair A.
Source: Grantee Submission. Mar 2017 119:1-20.
Peer Reviewed: Y
Page Count: 20
Publication Date: 2017
Sponsoring Agency: National Science Foundation (NSF)
Institute of Education Sciences (ED)
US Army Research Laboratory (ARL)
Office of Naval Research (ONR)
Contract Number: SBR9720314
REC0106965
REC0126265
ITR0325428
REESE0633918
ALT0834847
DRK120918409
1108845
R305H050169
R305B070349
R305A080589
R305A080594
R305A090528
R305A100875
R305C120001
W911INF1220030
N0001412C0643
N0001416C3027
Document Type: Journal Articles
Reports - Research
Descriptors: Intelligent Tutoring Systems, Computer Managed Instruction, Natural Language Processing, Instructional Design, Persuasive Discourse, Observation, Discourse Analysis, Instructional Effectiveness, Emotional Response, Dialogs (Language)
ISSN: 0161-4681
Abstract: Background: Pedagogical agents are computerized talking heads or embodied animated avatars that help students learn by performing actions and holding conversations with the students in natural language. Dialogues occur between a tutor agent and the student in the case of AutoTutor and other intelligent tutoring systems with natural language conversation. The agents are adaptive to the students' actions, verbal contributions, and in some systems their emotions (such as boredom, confusion, and frustration). Focus of Study: This paper explores several designs of trialogues (two agents interacting with a human student) that have been have been productively implemented for particular students, subject matters, and depths of learning. The two agents take on different roles, but often serve as peers and tutors. There are different trialogue designs that address different pedagogical goals for different classes of students. For example, students can (a) observe vicariously two agents interacting, (b) converse with a tutor agent while a peer agent periodically chimes in, or (c) teach a peer agent while a tutor rescues a problematic interaction. In addition, agents can argue with each other over issues and ask what the human student thinks about the argument. Research Design: Trialogues have been developed for systematic experimental investigations in several studies that measure student impressions, learning gains from pre-test to post-test on objective tests, and both cognitive and affective states during learning. The studies compare conditions with different pedagogical principles underlying the trialogues in order to assess the impact of these principles on student impressions, learning, emotions, and other psychological measures. Discourse analyses are performed on the language and actions in the log files in order to assess their impacts on psychological measures. Recommedations: Tests of these agent-based systems have shown improvements in learning gains and systematic influences on student emotions. In the future, researchers need to conduct more research to empirically evaluate the psychological impact of different trialogue designs on psychological measures. These trialogue designs range from scripted interactions between agents being observed by the student to the student helping a fellow peer agent and to the student resolving an argument between two agents. The central question is whether the learning experiences and outcomes show improvement over typical human-computer dialogues (i.e., 1 human and 1 tutor agent) and conventional pedagogical interventions.
Abstractor: As Provided
Number of References: 48
IES Funded: Yes
Entry Date: 2018
Accession Number: ED586945
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=ED586945
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: ED586945
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Two Heads May Be Better than One: Learning from Computer Agents in Conversational Trialogues
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Graesser%2C+Arthur+C%2E%22">Graesser, Arthur C.</searchLink><br /><searchLink fieldCode="AR" term="%22Forsyth%2C+Carol+M%2E%22">Forsyth, Carol M.</searchLink><br /><searchLink fieldCode="AR" term="%22Lehman%2C+Blair+A%2E%22">Lehman, Blair A.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Grantee+Submission%22"><i>Grantee Submission</i></searchLink>. Mar 2017 119:1-20.
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 20
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2017
– Name: SourceSuprt
  Label: Sponsoring Agency
  Group: SrcSuprt
  Data: National Science Foundation (NSF)<br />Institute of Education Sciences (ED)<br />US Army Research Laboratory (ARL)<br />Office of Naval Research (ONR)
– Name: NumberContract
  Label: Contract Number
  Group: NumCntrct
  Data: SBR9720314<br />REC0106965<br />REC0126265<br />ITR0325428<br />REESE0633918<br />ALT0834847<br />DRK120918409<br />1108845<br />R305H050169<br />R305B070349<br />R305A080589<br />R305A080594<br />R305A090528<br />R305A100875<br />R305C120001<br />W911INF1220030<br />N0001412C0643<br />N0001416C3027
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Intelligent+Tutoring+Systems%22">Intelligent Tutoring Systems</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Managed+Instruction%22">Computer Managed Instruction</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Language+Processing%22">Natural Language Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Instructional+Design%22">Instructional Design</searchLink><br /><searchLink fieldCode="DE" term="%22Persuasive+Discourse%22">Persuasive Discourse</searchLink><br /><searchLink fieldCode="DE" term="%22Observation%22">Observation</searchLink><br /><searchLink fieldCode="DE" term="%22Discourse+Analysis%22">Discourse Analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Instructional+Effectiveness%22">Instructional Effectiveness</searchLink><br /><searchLink fieldCode="DE" term="%22Emotional+Response%22">Emotional Response</searchLink><br /><searchLink fieldCode="DE" term="%22Dialogs+%28Language%29%22">Dialogs (Language)</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0161-4681
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Pedagogical agents are computerized talking heads or embodied animated avatars that help students learn by performing actions and holding conversations with the students in natural language. Dialogues occur between a tutor agent and the student in the case of AutoTutor and other intelligent tutoring systems with natural language conversation. The agents are adaptive to the students' actions, verbal contributions, and in some systems their emotions (such as boredom, confusion, and frustration). Focus of Study: This paper explores several designs of trialogues (two agents interacting with a human student) that have been have been productively implemented for particular students, subject matters, and depths of learning. The two agents take on different roles, but often serve as peers and tutors. There are different trialogue designs that address different pedagogical goals for different classes of students. For example, students can (a) observe vicariously two agents interacting, (b) converse with a tutor agent while a peer agent periodically chimes in, or (c) teach a peer agent while a tutor rescues a problematic interaction. In addition, agents can argue with each other over issues and ask what the human student thinks about the argument. Research Design: Trialogues have been developed for systematic experimental investigations in several studies that measure student impressions, learning gains from pre-test to post-test on objective tests, and both cognitive and affective states during learning. The studies compare conditions with different pedagogical principles underlying the trialogues in order to assess the impact of these principles on student impressions, learning, emotions, and other psychological measures. Discourse analyses are performed on the language and actions in the log files in order to assess their impacts on psychological measures. Recommedations: Tests of these agent-based systems have shown improvements in learning gains and systematic influences on student emotions. In the future, researchers need to conduct more research to empirically evaluate the psychological impact of different trialogue designs on psychological measures. These trialogue designs range from scripted interactions between agents being observed by the student to the student helping a fellow peer agent and to the student resolving an argument between two agents. The central question is whether the learning experiences and outcomes show improvement over typical human-computer dialogues (i.e., 1 human and 1 tutor agent) and conventional pedagogical interventions.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: Ref
  Label: Number of References
  Group: RefInfo
  Data: 48
– Name: CodeSource
  Label: IES Funded
  Group: SrcInfo
  Data: Yes
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2018
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED586945
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED586945
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 1
    Subjects:
      – SubjectFull: Intelligent Tutoring Systems
        Type: general
      – SubjectFull: Computer Managed Instruction
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Instructional Design
        Type: general
      – SubjectFull: Persuasive Discourse
        Type: general
      – SubjectFull: Observation
        Type: general
      – SubjectFull: Discourse Analysis
        Type: general
      – SubjectFull: Instructional Effectiveness
        Type: general
      – SubjectFull: Emotional Response
        Type: general
      – SubjectFull: Dialogs (Language)
        Type: general
    Titles:
      – TitleFull: Two Heads May Be Better than One: Learning from Computer Agents in Conversational Trialogues
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Graesser, Arthur C.
      – PersonEntity:
          Name:
            NameFull: Forsyth, Carol M.
      – PersonEntity:
          Name:
            NameFull: Lehman, Blair A.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Type: published
              Y: 2017
          Identifiers:
            – Type: issn-print
              Value: 0161-4681
          Numbering:
            – Type: volume
              Value: 119
          Titles:
            – TitleFull: Grantee Submission
              Type: main
ResultId 1