Chatbots systems, despite their popularity in today’s HCI and CSCW researches, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined user inputs with some scripted responses; or 2) they are designed with a focus on a single user scenario, and therefore little is known about these systems’ influence on other users in a community. In this paper, we present a research project that aims to develop a generalizable chatbot architecture to provide social support for community members in an online health community. The architecture is based on advanced neural network algorithms, thus it can handle new inputs from users and generate a variety of responses to them. The system is also generalizable as it can be easily migrate to other online communities. With a follow-up field experiment with the chatbot deployed back into the community, we illustrate the system’s usefulness in providing emotional supporting to individual members. In addition, our study provides empirical understandings to fill the research gap on how a social-support chatbot can positively impact the community engagement.
https://doi.org/10.1145/3449083
The 24th ACM Conference on Computer-Supported Cooperative Work and Social Computing