Yizhou Hu

Feng Chen, Luna Xingyu Li, Ray-Yuan Chung et al.

Digital portals in retirement communities often create physical and cognitive barriers for older adults, leading to digital avoidance. Generative AI offers a solution by enabling natural language interaction, yet its adoption is hindered by the opaque, "Black Box" nature of these systems and lingering usability challenges. To address this, we evaluated a voice-enabled Large Language Model (LLM) chatbot at a continuing care retirement community in the Pacific Northwest. Through a mixed-methods Co-Design and Literacy Workshop (N=25), we applied a "Glass Box" approach combining multimodal accessibility with intentional AI education. The intervention significantly improved participants' technical understanding (p=0.004) and perceived transparency (p=0.001), shifting their interaction model from blind trust to informed reliance prioritizing verifiable evidence. While voice input reduced cognitive load, usability scores dropped significantly for users aged 80 and older (r=-0.50), indicating that truly age-inclusive AI must evolve beyond touch-based interfaces toward zero-touch navigation.

Jindong Chen, Yizhou Hu, Jingping Liu et al.

Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough contextual information, which poses a great challenge for classification. In this paper, we retrieve knowledge from external knowledge source to enhance the semantic representation of short texts. We take conceptual information as a kind of knowledge and incorporate it into deep neural networks. For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA). We utilize Concept towards Short Text (C- ST) attention and Concept towards Concept Set (C-CS) attention to acquire the weight of concepts from two aspects. And we classify a short text with the help of conceptual information. Unlike traditional approaches, our model acts like a human being who has intrinsic ability to make decisions based on observation (i.e., training data for machines) and pays more attention to important knowledge. We also conduct extensive experiments on four public datasets for different tasks. The experimental results and case studies show that our model outperforms the state-of-the-art methods, justifying the effectiveness of knowledge powered attention.