Active CR Engagement
Active CR engagement research focuses on improving the effectiveness and efficiency of crisis responder interactions, particularly in mental health contexts, by leveraging AI-driven tools. Current research employs various machine learning models, including transformers, recurrent neural networks, and graph neural networks, to analyze multimodal data (e.g., text, audio, video) and predict engagement levels, identify key issues, and optimize resource allocation. This work has significant implications for enhancing the quality and scalability of crisis response systems, ultimately improving the support provided to individuals in need.
Papers
Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning
Majeed Kazemitabaar, Oliver Huang, Sangho Suh, Austin Z. Henley, Tovi Grossman
DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Jia Li, Yangchen Yu, Yin Chen, Yu Zhang, Peng Jia, Yunbo Xu, Ziqiang Li, Meng Wang, Richang Hong