Specially, these projects are involved in our large AI4EDU plans to support our vision of creating better real-world AI systems for education.

StoryBuddy:A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement

Abstract: Despite its benefits for children’s skill development and parentchild bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions. While recent advances made AI generation of questions from stories possible, the fully-automated approach excludes parent involvement, disregards educational goals, and underoptimizes for child engagement. Informed by need-finding interviews and participatory design (PD) results, we developed StoryBuddy, an AI-enabled system for parents to create interactive storytelling experiences. StoryBuddy’s design highlighted the need for accommodating dynamic user needs between the desire for parent involvement and parent-child bonding and the goal of minimizing parent intervention when busy. The PD revealed varied assessment and educational goals of parents, which StoryBuddy addressed by supporting configuring question types and tracking child progress. A user study validated StoryBuddy’s usability and suggested design insights for future parent-AI collaboration systems.

AI supported Hybrid Learning Paradigm

Abstract: Recently, Northeastern post a novel cross-campus livestreaming classroom paradigm—students from different geo-locations can take the same course simultaneously, with one class being taught in person by the lecturer and the other classes joining via live-streaming at different campuses with an in-person teaching assistant (TA). Our study aims to bridge this gap through a multi-site in-field observation study and a semi-structured interview at four Northeastern campuses (Boston, Bay Area, Seattle, and Vancouver). We expect to derive insights for new pedagogical practices and novel technological innovations (in particular LLM-based AI) to accommodate an intelligent and efficient remote education paradigm and the sustainable growth of the global network at Northeastern University.

StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children’s Story-Based Learning

Abstract: Interactive story reading is common in early childhood education, where teachers expect to teach both language skills and real-world knowledge beyond the story. While many story reading systems have been developed for this activity, they often fail to infuse real-world knowledge into the conversation. This limitation can be attributed to the existing questionanswering (QA) datasets used for children’s education, upon which the systems are built, failing to capture the nuances of how education experts think when conducting interactive story reading activities. To bridge this gap, we design an annotation framework, empowered by existing knowledge graph to capture experts’ annotations and thinking process, and leverage this framework to construct StorySparkQA dataset, which comprises 5, 868 expert-annotated QA pairs with real-world knowledge. We conduct automated and human expert evaluations across various QA pair generation settings to demonstrate that our StorySparkQA can effectively support models in generating QA pairs that target real-world knowledge beyond story content. StorySparkQA is available at https://huggingface.co/datasets/NEU-HAI/StorySparkQA.