CASS

Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many systems use a rule-based dialog flow, thus they can only respond to limited number pre-defined inputs with pre-scripted responses; or 2) are designed focus on single-user scenarios, it is unclear how these may affect other users community. In this paper, we develop generalizable chatbot architecture (CASS) provide social support community members an online health The CASS based advanced neural network algorithms, handle new from generate variety responses them. also as be easily migrate communities. With follow-up field experiment, proven useful supporting individual who seek emotional support. Our work contributes fill research gap influence whole community's engagement.