<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>DSpace Collection:</title>
    <link>https://repository.isls.org/handle/1/11211</link>
    <description />
    <pubDate>Sun, 22 Nov 2026 06:33:33 GMT</pubDate>
    <dc:date>2026-11-22T06:33:33Z</dc:date>
    <image>
      <title>DSpace Collection:</title>
      <url>http://https://repository.isls.org:8080/retrieve/814b89b4-8703-40af-af99-b4999489d370/ISLS2025-logo.png</url>
      <link>https://repository.isls.org/handle/1/11211</link>
    </image>
    <item>
      <title>"Memorize the Source!" — Does Focusing on Learning Partners Improve Source Memory Without Impairing Content Learning?</title>
      <link>https://repository.isls.org/handle/1/11965</link>
      <description>Title: "Memorize the Source!" — Does Focusing on Learning Partners Improve Source Memory Without Impairing Content Learning?
Authors: Ülker, Oktay; Bodemer, Daniel
Abstract: Remembering which learning partner shared certain information (source memory) helps learners to identify whom to approach for more information (academic help-seeking). Research suggests that while explicit tasks to remember sources can improve source memory, they may also impair learning the content. Our experimental pseudo-collaborative study (112 participants) applied a 2×2 between-subjects design (with vs. without source-related and content-related tasks), testing beneficial or detrimental effects of tasks on source memory and learning. Participants received information from three learning partners with different knowledge levels (high vs. medium vs. low). Source memory and learning correlated positively but were not influenced overall by tasks. However, content-related tasks improved source memory for high-knowledge partners. Supplementary analyses of two real collaborating groups revealed that source-related tasks promote self-regulative strategies (taking notes who said what). Our complementary results indicate that learners might need tasks with more guidance targeting group-level processes to support source memory in collaborative learning.
Description: Long Paper</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://repository.isls.org/handle/1/11965</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Collaborative Math Learning Facilitated by an Intelligent Agent</title>
      <link>https://repository.isls.org/handle/1/11966</link>
      <description>Title: Collaborative Math Learning Facilitated by an Intelligent Agent
Authors: Lee, Melissa; Feng, Mingyu; Miller, Matt
Abstract: Collaborative learning, a proven method for supporting differentiated learning, is often underutilized in schools, particularly when there are staffing challenges to facilitate and monitor group interactions. OKO is an intelligent platform for small-group collaborative learning in elementary and middle school classrooms, with an initial focus on math games and puzzles. It leverages an Artificial Intelligence-based agent to interact with small groups of students, facilitating social and collaborative activities. This paper introduces the OKO collaborative learning platform and examines how using OKO in small groups over a two-week period in classrooms affected student math learning, attitudes towards math, and collaboration skills. Despite a short implementation period, findings suggest that OKO shows promise in improving math learning and reducing math anxiety. The paper also discusses how teacher training can better support implementation of the program in classrooms.
Description: Long Paper</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://repository.isls.org/handle/1/11966</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Capturing Collaborative Competency with GPT-4o and ENA</title>
      <link>https://repository.isls.org/handle/1/11963</link>
      <description>Title: Capturing Collaborative Competency with GPT-4o and ENA
Authors: Lee, Yoonjae; Kwon, Christine; Seoh, Sarah; Gweon, Gahgene; Stamper, John; Rosé, Carolyn P.
Abstract: Collaboration is a critical learning skill employed across many educational domains. Since moments of collaborative competencies frequently occur in student discourse, there has been a growing body of work in automatic collaborative process analysis. With recent advancements in Large Language Models (LLMs), it became feasible to automate the collaborative process analysis through simple prompting methods. In this study, we develop CoComTag, an LLM-powered approach using GPT-4o that captures students' collaborative competency using four prompting techniques. Our findings demonstrate that CoComTag shows substantial agreement with humans (kappa of 0.67). Such a result shows that LLM yields comparable performance with prior studies using only prompting strategies without additional fine-tuning. Next, using qualitative error analysis and epistemic network analysis (ENA), we examine how CoComTag differs from humans in detecting collaborative competency. Our analysis shows that ENA provides visual cues on where collaborative competencies co-occur, revealing the differences between LLM and human annotation patterns.
Description: Long Paper</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://repository.isls.org/handle/1/11963</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>A Clustering Approach to Collaborative Problem Solving: Utilizing Discourse and Trace Log Data</title>
      <link>https://repository.isls.org/handle/1/11964</link>
      <description>Title: A Clustering Approach to Collaborative Problem Solving: Utilizing Discourse and Trace Log Data
Authors: Hong, Daeun; Feng, Chen; Zou, Xiaotian; Huang, Sijia; Hmelo-Silver, Cindy E.; Wang, Tianshu; Acosta, Halim; Glazewski, Krista; Lester, James C.
Abstract: The paper proposes a collaborative problem solving (CPS) clustering approach using a set of CPS indicators derived from process and discourse data to capture students' CPS practices within a CSCL context. We utilized a dataset generated from 68 middle schoolers in 17 groups interacting with a game-based CSCL environment as the clustering model input. We identify four patterns of CPS engagement and examine whether the model effectively conveys information regarding students’ CPS engagement in relation to their learning performance. Lastly, we discuss the implications of the approach and its potential for further development.
Description: Long Paper</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://repository.isls.org/handle/1/11964</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
  </channel>
</rss>

