Researchers have developed an automated discourse analysis system (ADAS) to classify teacher and student utterances in science classrooms, aiming to understand knowledge construction and improve teaching. The system uses joint multi-task learning and LLM-based synthetic data augmentation to address label imbalance. A zero-shot GPT-5.4 baseline achieved macro-F1 scores of 0.467 for Utterance Type and 0.476 for Reasoning Component classification, with findings indicating that teacher feedback-with-question moves precede student inferential reasoning. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT This research could lead to more effective AI tools for analyzing educational interactions and improving teaching methods.
RANK_REASON This is a research paper detailing a new method for analyzing classroom discourse using AI.
