<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>When a Reading Club Meets a Robotic Don Quixote: Embodied GenAI for Literary Dialogue⋆</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Dan Kohen-Vacs</string-name>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Gila Kurtz</string-name>
          <email>gilaku@hit.ac.il</email>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Holon Institute of Technology (HIT)</institution>
          ,
          <addr-line>52 Golomb Street, POB 305 Holon 5810201</addr-line>
        </aff>
      </contrib-group>
      <pub-date>
        <year>2025</year>
      </pub-date>
      <abstract>
        <p>Recent integrations between Social Robotics (SR) and Generative Artificial Intelligence (GenAI) are opening new avenues for applications within the humanities [1-3]. In this abstract, we present RoBook, a social robot-led book club centered on Don Quixote by Cervantes. We employ NAO, the SR, inviting participants to interact with the novel's protagonist while taking on the roles of other characters. In this effort, we draw on SR's potential to enrich the book club through dynamic educational interactions. We offer an experience in which a group of participants engage deeply with literature, explore diverse perspectives, and take ownership of their learning processes [4]. RoBook builds on our prior findings that highlight NAO's role as a motivational catalyst in learning experiences [1, 5]. Our design was guided by five principles of the Educational Robotics Application (ERA) Framework: Intelligence, Interaction, Engagement, Equity, and Practical [6]. We align our design efforts of RoBook with current trends that are disrupting and transforming learning interactions by embodying GenAI within the field of Social Robotics. Accordingly, we propose extending the ERA framework to include advancements in Social Robotics and Generative AI. RoBook is structured for groups of 4 participants, who engage in four sequential phases. In the first phase, NAO introduces the book club and prompts participants to present their assigned character from the novel in the style of a dramatic performance. In the second phase, participants and NAO construct a scene, selecting props such as armor, clothing, and scenery that reflect the book's historical context. In the third phase, participants watch a short video related to Don Quixote and are invited to pose questions to its robotic representation. These may include philosophical or ethical inquiries that extend beyond the book's plot. The robot responds using GenAI, drawing from the values and spirit of the original text. In the final phase, NAO introduces global warming as a contemporary moral challenge and invites participants to respond. Based on their input, it generates a reflective monologue in character, expressing Don Quixote's imagined response to this modern dilemma. We use the OpenAI API for dialogue and PlayHT to generate a voice evocative of a Spanish knight. These outputs are accompanied by physical gestures and expressive animations, enhancing the robot's emotional presence and narrative realism. Additionally, NAO is equipped to detect visual markers and spoken keywords, enabling it to respond contextually throughout the activity. Preliminary results from four pilot sessions, each involving a group of higher education students, indicate that the activity was perceived as both educationally enriching and appealing. Participants described the experience as playful, surprising, and engaging. Most reported a deeper understanding of literary themes and character dynamics, particularly through the interaction with the robot. RoBook exemplifies our approach, reflecting the principles of ERA contextualized within contemporary advancements in SR empowered by GenAI, enabling to offer a book club experience that is vivid, immersive, engaging, and appealing.</p>
      </abstract>
      <kwd-group>
        <kwd>eol&gt;RoBook</kwd>
        <kwd>Social Robot (SR)</kwd>
        <kwd>Human-Robot Interaction</kwd>
        <kwd>Generative Artificial-Intelligence (GenAI)</kwd>
        <kwd>ReadingClub</kwd>
        <kwd>Literacy Education 1</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Declaration on Generative AI
During the preparation of this work, the authors used Chat-GPT-4 and Grammarly in order to
Grammar and spelling check. After using these tools/services, the authors reviewed and edited the
content as needed and take(s) full responsibility for the publication’s content.</p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          [1]
          <string-name>
            <given-names>D.</given-names>
            <surname>Kohen-Vacs</surname>
          </string-name>
          et al., “
          <article-title>Towards a call for transformative practices in academia enhanced by generative AI</article-title>
          .,”
          <source>European Journal of Open</source>
          , Distance &amp; E-Learning, vol.
          <volume>26</volume>
          , no.
          <issue>1</issue>
          ,
          <year>2024</year>
          .
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          [2]
          <string-name>
            <given-names>G.</given-names>
            <surname>Kurtz</surname>
          </string-name>
          et al., “
          <article-title>Strategies for Integrating Generative AI into Higher Education: Navigating Challenges and Leveraging Opportunities,” Education Sciences</article-title>
          , vol.
          <volume>14</volume>
          , no.
          <issue>5</issue>
          , p.
          <fpage>503</fpage>
          , May
          <year>2024</year>
          , doi: 10.3390/educsci14050503.
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          [3]
          <string-name>
            <given-names>B.</given-names>
            <surname>Obrenovic</surname>
          </string-name>
          ,
          <string-name>
            <given-names>X.</given-names>
            <surname>Gu</surname>
          </string-name>
          ,
          <string-name>
            <given-names>G.</given-names>
            <surname>Wang</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D.</given-names>
            <surname>Godinic</surname>
          </string-name>
          ,
          <string-name>
            <surname>and I. Jakhongirov</surname>
          </string-name>
          , “
          <article-title>Generative AI and humanrobot interaction: implications and future agenda for business, society</article-title>
          and ethics,”
          <source>AI &amp; Soc</source>
          , vol.
          <volume>40</volume>
          , no.
          <issue>2</issue>
          , pp.
          <fpage>677</fpage>
          -
          <lpage>690</lpage>
          , Feb.
          <year>2025</year>
          , doi: 10.1007/s00146-024-01889-0.
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          [4]
          <string-name>
            <given-names>J.</given-names>
            <surname>Taggart</surname>
          </string-name>
          and
          <string-name>
            <given-names>L. B.</given-names>
            <surname>Wheeler</surname>
          </string-name>
          , “
          <article-title>Collaborative learning as constructivist practice: An exploratory qualitative descriptive study of faculty approaches to student group work,” Active Learning in Higher Education</article-title>
          , vol.
          <volume>26</volume>
          , no.
          <issue>1</issue>
          , pp.
          <fpage>59</fpage>
          -
          <lpage>76</lpage>
          , Mar.
          <year>2025</year>
          , doi: 10.1177/14697874231193938.
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          [5]
          <string-name>
            <given-names>G.</given-names>
            <surname>Kurtz and D.</surname>
          </string-name>
          Kohen-Vacs, “
          <article-title>Humanoid robot as a tutor in a team-based training activity,” Interactive Learning Environments</article-title>
          , vol.
          <volume>32</volume>
          , no.
          <issue>1</issue>
          , pp.
          <fpage>340</fpage>
          -
          <lpage>354</lpage>
          , Jan.
          <year>2024</year>
          , doi: 10.1080/10494820.
          <year>2022</year>
          .
          <volume>2086577</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          [6]
          <string-name>
            <given-names>D.</given-names>
            <surname>Catlin</surname>
          </string-name>
          and
          <string-name>
            <given-names>M.</given-names>
            <surname>Blamires</surname>
          </string-name>
          , “
          <article-title>The Principles of Educational Robotic Applications (ERA): A framework for understanding and developing educational robots and their activities</article-title>
          ,
          <source>” The 12th EuroLogo Conference</source>
          ,
          <year>2010</year>
          .
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>