Search for: All records

In an age where artificial intelligence (AI) plays an increasingly pivotal role in daily life, it is essential to equip our youngest learners with foundational knowledge of AI. The AI by 8 project aims to empower kindergarten through second grade teachers in rural North Carolina by introducing AI concepts through engaging, unplugged activities integrated into English Language Arts (ELA) instruction. This initiative seeks to address the gap in AI education expertise among early childhood educators and seeks to foster a generation of students who are well-prepared to navigate a technology-driven future. We present in this poster the guiding theoretical framework for our work, outlining the objectives of the research-practice partnership, and our initial efforts at recruiting rural K-2 teachers. 

Understanding the relationship between student behaviors and learning outcomes is crucial for designing effective collaborative learning environments. However, collaborative learning analytics poses significant challenges, not only due to the complex interplay between collaborative problem-solving and collaborative dialogue but also due to the need for model interpretability. To address these challenges, this paper introduces a multi-view predictive student modeling framework using causal graph discovery. We first extract interpretable behavioral features from students' collaborative dialogue data and game trace logs to predict student learning within a collaborative game-based learning environment. We then apply constraint-based sequential pattern mining to identify cognitive and social behavioral patterns in student's data to improve predictive power. We employ unified causal modeling for interpreting model outputs, using causal discovery methods to reveal key interactions among student behaviors that significantly contribute to predicting learning outcomes and identifying frequent collaborative problem-solving skills. Evaluations of the predictive student modeling framework show that combining features from dialogue and in-game behaviors improves the prediction of student learning gains. The findings highlight the potential of multi-view behavioral data and causal analysis to improve both the effectiveness and the interpretability of collaborative learning analytics. 

Abstract Understanding students’ multi-party epistemic and topic based-dialogue contributions, or how students present knowledge in group-based chat interactions during collaborative game-based learning, offers valuable insights into group dynamics and learning processes. However, manually annotating these contributions is labor-intensive and challenging. To address this, we develop an automated method for recognizing dialogue acts from text chat data of small groups of middle school students interacting in a collaborative game-based learning environment. Our approach utilizes dual contrastive learning and label-aware data augmentation to fine-tune large language models’ underlying embedding representations within a supervised learning framework for epistemic and topic-based dialogue act classification. Results show that our method achieves a performance improvement of 4% to 8% over baseline methods in two key classification scenarios. These findings highlight the potential for automated dialogue act recognition to support understanding of how meaning-making occurs by focusing on the development and evolution of knowledge in group discourse, ultimately providing teachers with actionable insights to better support student learning.