IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v17y2025i2p52-d1572554.html
   My bibliography  Save this article

Enhancing Human–Agent Interaction via Artificial Agents That Speculate About the Future

Author

Listed:
  • Casey C. Bennett

    (School of Computing, DePaul University, Chicago, IL 60604, USA
    Department of Data Science, Hanyang University, Seoul 04763, Republic of Korea)

  • Young-Ho Bae

    (Department of Data Science, Hanyang University, Seoul 04763, Republic of Korea)

  • Jun-Hyung Yoon

    (Department of Data Science, Hanyang University, Seoul 04763, Republic of Korea)

  • Say Young Kim

    (Department of English Language & Literature, Hanyang University, Seoul 04763, Republic of Korea)

  • Benjamin Weiss

    (Quality and Usability Lab, Technische Universität Berlin, 10623 Berlin, Germany)

Abstract

Human communication in daily life entails not only talking about what we are currently doing or will do, but also speculating about future possibilities that may (or may not) occur, i.e., “anticipatory speech”. Such conversations are central to social cooperation and social cohesion in humans. This suggests that such capabilities may also be critical for developing improved speech systems for artificial agents, e.g., human–agent interaction (HAI) and human–robot interaction (HRI). However, to do so successfully, it is imperative that we understand how anticipatory speech may affect the behavior of human users and, subsequently, the behavior of the agent/robot. Moreover, it is possible that such effects may vary across cultures and languages. To that end, we conducted an experiment where a human and autonomous 3D virtual avatar interacted in a cooperative gameplay environment. The experiment included 40 participants, comparing different languages (20 English, 20 Korean), where the artificial agent had anticipatory speech either enabled or disabled. The results showed that anticipatory speech significantly altered the speech patterns and turn-taking behavior of both the human and the agent, but those effects varied depending on the language spoken. We discuss how the use of such novel communication forms holds potential for enhancing HAI/HRI, as well as the development of mixed reality and virtual reality interactive systems for human users.

Suggested Citation

  • Casey C. Bennett & Young-Ho Bae & Jun-Hyung Yoon & Say Young Kim & Benjamin Weiss, 2025. "Enhancing Human–Agent Interaction via Artificial Agents That Speculate About the Future," Future Internet, MDPI, vol. 17(2), pages 1-21, January.
    • Handle: RePEc:gam:jftint:v:17:y:2025:i:2:p:52-:d:1572554
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/17/2/52/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1999-5903/17/2/52/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gregg A. Castellucci & Christopher K. Kovach & Matthew A. Howard & Jeremy D. W. Greenlee & Michael A. Long, 2022. "A speech planning network for interactive language use," Nature, Nature, vol. 602(7895), pages 117-122, February.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Lingyun Zhao & Xiaoqin Wang, 2023. "Frontal cortex activity during the production of diverse social communication calls in marmoset monkeys," Nature Communications, Nature, vol. 14(1), pages 1-17, December.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jftint:v:17:y:2025:i:2:p:52-:d:1572554. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.