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

2025-11-14

AI Summary

This study addresses low collaborative learning engagement and inequitable AI tool access in higher education across the Global South, developing and deploying an LLM-integrated real-time collaborative learning platform for undergraduate students in Bangladesh. Methodologically, we propose a “fairness-aware human–AI co-design framework” featuring dynamic turn-taking allocation, interaction transparency, and a dual-mode (individual/group) learning space architecture to enhance LLM role legitimacy and contribution equity in collaboration. Effectiveness was evaluated via pre-/post-intervention surveys and correlation analysis. Results indicate high platform usability (83% rated it reliable), low user frustration (83% reported no stress), and strong perceived value of LLM assistance (92% endorsement), with significant positive correlation between expected and experienced utility (r = 0.61). The framework establishes a reusable design paradigm for equitable, trustworthy educational AI deployment in resource-constrained settings.

Technology Category

• Humans and AI: AI for Accessibility
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Developing AI-enhanced collaborative learning platform with LLM support
• Evaluating LLM integration for equitable participation in group discussions
• Assessing AI-mediated collaboration in Global South higher education context

Innovation

• AI platform embeds LLMs in individual and group study panels
• Uses LLMs to support real-time collaboration among students
• Designed to promote equitable turn-taking and transparency