Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CollaClassroom: An AI-Augmented Collaborative Learning Platform with LLM Support in the Context of Bangladeshi University Students

Salman Sayeed, Bijoy Ahmed Saiem, Al-Amin Sany, Sadia Sharmin, A. B. M. Alim Al Islam

TL;DR

CollaClassroom integrates dual LLM channels—a personal tutor in My Chatter and a group co-author in Group Chatter—within a shared knowledge base to support equitable, real-time collaboration among Bangladeshi university students. In a small-N study (N=12), the authors evaluate usability, engagement, and learning outcomes via pre-post surveys, descriptive statistics, chi-square tests, and Pearson correlations, reporting strong links between perceived equal participation and meaningful contribution (r = 0.86) and solid alignment between initial expectations and post-use assessments (r ≈ 0.61). Results show high usability with easy learnability and low frustration, though modest cognitive load suggests productive cognitive effort rather than burden. The study provides design implications for fairness-aware orchestration of human–AI teamwork in lower-resource higher-education contexts, and points to scalable, longer-term evaluations to validate transfer and generalizability across disciplines.

Abstract

CollaClassroom is an AI-enhanced platform that embeds large language models (LLMs) into both individual and group study panels to support real-time collaboration. We evaluate CollaClassroom with Bangladeshi university students (N = 12) through a small-group study session and a pre-post survey. Participants have substantial prior experience with collaborative learning and LLMs and express strong receptivity to LLM-assisted study (92% agree/strongly agree). Usability ratings are positive, including high learnability(67% "easy"), strong reliability (83% "reliable"), and low frustration (83% "not at all"). Correlational analyses show that participants who perceive the LLM as supporting equal participation also view it as a meaningful contributor to discussions (r = 0.86). Moreover, their pre-use expectations of LLM value align with post-use assessments (r = 0.61). These findings suggest that LLMs can enhance engagement and perceived learning when designed to promote equitable turn-taking and transparency across individual and shared spaces. The paper contributes an empirically grounded account of AI-mediated collaboration in a Global South higher-education context, with design implications for fairness-aware orchestration of human-AI teamwork.

CollaClassroom: An AI-Augmented Collaborative Learning Platform with LLM Support in the Context of Bangladeshi University Students

TL;DR

CollaClassroom integrates dual LLM channels—a personal tutor in My Chatter and a group co-author in Group Chatter—within a shared knowledge base to support equitable, real-time collaboration among Bangladeshi university students. In a small-N study (N=12), the authors evaluate usability, engagement, and learning outcomes via pre-post surveys, descriptive statistics, chi-square tests, and Pearson correlations, reporting strong links between perceived equal participation and meaningful contribution (r = 0.86) and solid alignment between initial expectations and post-use assessments (r ≈ 0.61). Results show high usability with easy learnability and low frustration, though modest cognitive load suggests productive cognitive effort rather than burden. The study provides design implications for fairness-aware orchestration of human–AI teamwork in lower-resource higher-education contexts, and points to scalable, longer-term evaluations to validate transfer and generalizability across disciplines.

Abstract

CollaClassroom is an AI-enhanced platform that embeds large language models (LLMs) into both individual and group study panels to support real-time collaboration. We evaluate CollaClassroom with Bangladeshi university students (N = 12) through a small-group study session and a pre-post survey. Participants have substantial prior experience with collaborative learning and LLMs and express strong receptivity to LLM-assisted study (92% agree/strongly agree). Usability ratings are positive, including high learnability(67% "easy"), strong reliability (83% "reliable"), and low frustration (83% "not at all"). Correlational analyses show that participants who perceive the LLM as supporting equal participation also view it as a meaningful contributor to discussions (r = 0.86). Moreover, their pre-use expectations of LLM value align with post-use assessments (r = 0.61). These findings suggest that LLMs can enhance engagement and perceived learning when designed to promote equitable turn-taking and transparency across individual and shared spaces. The paper contributes an empirically grounded account of AI-mediated collaboration in a Global South higher-education context, with design implications for fairness-aware orchestration of human-AI teamwork.

Paper Structure

This paper contains 27 sections, 6 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Collaborative Learning
  4. LLM in Education
  5. AI adoption in education sector of Bangladesh
  6. LLM Integration in Collaborative Learning
  7. Methodology
  8. Participants
  9. Participants Engagement
  10. Study Design
  11. Survey Instrument
  12. Data Collection and Procedure
  13. Data Analysis
  14. Ethical Considerations
  15. Findings
  16. ...and 12 more sections

Figures (6)

  • Figure 1: Overview of CollaClassroom, showing the main features
  • Figure 2: User Interface of the four panels of the CollaClassroom
  • Figure 3: Data Collection and Analysis Workflow of CollaClassroom
  • Figure 4: Prior experience with AI/LLM tools in study/work (N=12)
  • Figure 5: Would integrating an LLM into your study sessions help? (N=12)
  • ...and 1 more figures