Searching for Prototypical Facial Feedback Signals

Dirk K.J. Heylen, E. Bevacqua, M. Tellier, C. Pelachaud

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    15 Citations (Scopus)
    15 Downloads (Pure)

    Abstract

    Embodied conversational agents should be able to provide feedback on what a human interlocutor is saying. We are compiling a list of facial feedback expressions that signal attention and interest, grounding and attitude. As expressions need to serve many functions at the same time and most of the component signals are ambiguous, it is important to get a better idea of the many to many mappings between displays and functions. We asked people to label several dynamic expressions as a probe into this semantic space. We compare simple signals and combined signals in order to find out whether a combination of signals can have a meaning on its own or not, i. e. the meaning of single signals is different from the meaning attached to the combination of these signals. Results show that in some cases a combination of signals alters the perceived meaning of the backchannel.
    Original languageUndefined
    Title of host publicationIntelligent Virtual Agents
    EditorsC. Pelachaud, J-C. Martin, E. André, G. Chollet, D. Pelé
    Place of PublicationBerlin
    PublisherSpringer
    Pages147-153
    Number of pages7
    ISBN (Print)978-3-540-74996-7
    DOIs
    Publication statusPublished - 2007

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Number7/4722/2007
    Volume4722/2007

    Keywords

    • EWI-11839
    • METIS-245987
    • IR-62149
    • HMI-IA: Intelligent Agents

    Cite this

    Heylen, D. K. J., Bevacqua, E., Tellier, M., & Pelachaud, C. (2007). Searching for Prototypical Facial Feedback Signals. In C. Pelachaud, J-C. Martin, E. André, G. Chollet, & D. Pelé (Eds.), Intelligent Virtual Agents (pp. 147-153). [10.1007/978-3-540-74997-4_14] (Lecture Notes in Computer Science; Vol. 4722/2007, No. 7/4722/2007). Berlin: Springer. https://doi.org/10.1007/978-3-540-74997-4_14
    Heylen, Dirk K.J. ; Bevacqua, E. ; Tellier, M. ; Pelachaud, C. / Searching for Prototypical Facial Feedback Signals. Intelligent Virtual Agents. editor / C. Pelachaud ; J-C. Martin ; E. André ; G. Chollet ; D. Pelé. Berlin : Springer, 2007. pp. 147-153 (Lecture Notes in Computer Science; 7/4722/2007).
    @inbook{31eeb3abe25e4ea99a7d84fd1e0941be,
    title = "Searching for Prototypical Facial Feedback Signals",
    abstract = "Embodied conversational agents should be able to provide feedback on what a human interlocutor is saying. We are compiling a list of facial feedback expressions that signal attention and interest, grounding and attitude. As expressions need to serve many functions at the same time and most of the component signals are ambiguous, it is important to get a better idea of the many to many mappings between displays and functions. We asked people to label several dynamic expressions as a probe into this semantic space. We compare simple signals and combined signals in order to find out whether a combination of signals can have a meaning on its own or not, i. e. the meaning of single signals is different from the meaning attached to the combination of these signals. Results show that in some cases a combination of signals alters the perceived meaning of the backchannel.",
    keywords = "EWI-11839, METIS-245987, IR-62149, HMI-IA: Intelligent Agents",
    author = "Heylen, {Dirk K.J.} and E. Bevacqua and M. Tellier and C. Pelachaud",
    note = "10.1007/978-3-540-74997-4_14",
    year = "2007",
    doi = "10.1007/978-3-540-74997-4_14",
    language = "Undefined",
    isbn = "978-3-540-74996-7",
    series = "Lecture Notes in Computer Science",
    publisher = "Springer",
    number = "7/4722/2007",
    pages = "147--153",
    editor = "C. Pelachaud and J-C. Martin and E. Andr{\'e} and G. Chollet and D. Pel{\'e}",
    booktitle = "Intelligent Virtual Agents",

    }

    Heylen, DKJ, Bevacqua, E, Tellier, M & Pelachaud, C 2007, Searching for Prototypical Facial Feedback Signals. in C Pelachaud, J-C Martin, E André, G Chollet & D Pelé (eds), Intelligent Virtual Agents., 10.1007/978-3-540-74997-4_14, Lecture Notes in Computer Science, no. 7/4722/2007, vol. 4722/2007, Springer, Berlin, pp. 147-153. https://doi.org/10.1007/978-3-540-74997-4_14

    Searching for Prototypical Facial Feedback Signals. / Heylen, Dirk K.J.; Bevacqua, E.; Tellier, M.; Pelachaud, C.

    Intelligent Virtual Agents. ed. / C. Pelachaud; J-C. Martin; E. André; G. Chollet; D. Pelé. Berlin : Springer, 2007. p. 147-153 10.1007/978-3-540-74997-4_14 (Lecture Notes in Computer Science; Vol. 4722/2007, No. 7/4722/2007).

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    TY - CHAP

    T1 - Searching for Prototypical Facial Feedback Signals

    AU - Heylen, Dirk K.J.

    AU - Bevacqua, E.

    AU - Tellier, M.

    AU - Pelachaud, C.

    N1 - 10.1007/978-3-540-74997-4_14

    PY - 2007

    Y1 - 2007

    N2 - Embodied conversational agents should be able to provide feedback on what a human interlocutor is saying. We are compiling a list of facial feedback expressions that signal attention and interest, grounding and attitude. As expressions need to serve many functions at the same time and most of the component signals are ambiguous, it is important to get a better idea of the many to many mappings between displays and functions. We asked people to label several dynamic expressions as a probe into this semantic space. We compare simple signals and combined signals in order to find out whether a combination of signals can have a meaning on its own or not, i. e. the meaning of single signals is different from the meaning attached to the combination of these signals. Results show that in some cases a combination of signals alters the perceived meaning of the backchannel.

    AB - Embodied conversational agents should be able to provide feedback on what a human interlocutor is saying. We are compiling a list of facial feedback expressions that signal attention and interest, grounding and attitude. As expressions need to serve many functions at the same time and most of the component signals are ambiguous, it is important to get a better idea of the many to many mappings between displays and functions. We asked people to label several dynamic expressions as a probe into this semantic space. We compare simple signals and combined signals in order to find out whether a combination of signals can have a meaning on its own or not, i. e. the meaning of single signals is different from the meaning attached to the combination of these signals. Results show that in some cases a combination of signals alters the perceived meaning of the backchannel.

    KW - EWI-11839

    KW - METIS-245987

    KW - IR-62149

    KW - HMI-IA: Intelligent Agents

    U2 - 10.1007/978-3-540-74997-4_14

    DO - 10.1007/978-3-540-74997-4_14

    M3 - Chapter

    SN - 978-3-540-74996-7

    T3 - Lecture Notes in Computer Science

    SP - 147

    EP - 153

    BT - Intelligent Virtual Agents

    A2 - Pelachaud, C.

    A2 - Martin, J-C.

    A2 - André, E.

    A2 - Chollet, G.

    A2 - Pelé, D.

    PB - Springer

    CY - Berlin

    ER -

    Heylen DKJ, Bevacqua E, Tellier M, Pelachaud C. Searching for Prototypical Facial Feedback Signals. In Pelachaud C, Martin J-C, André E, Chollet G, Pelé D, editors, Intelligent Virtual Agents. Berlin: Springer. 2007. p. 147-153. 10.1007/978-3-540-74997-4_14. (Lecture Notes in Computer Science; 7/4722/2007). https://doi.org/10.1007/978-3-540-74997-4_14