Diplomat: A conversational agent framework for goal-oriented group discussion
This work provides a tool for researchers and developers in human-computer interaction to build conversational facilitators, but it is incremental as it builds on existing work without major breakthroughs.
The authors tackled the lack of tooling for conversational agents in group goal-oriented discussions by creating Diplomat, a Python-based framework that supports simple agent specification and integration with chat services, as documented in a preliminary user study and shared on GitHub.
Recent work in human-computer interaction has explored the use of conversational agents as facilitators for group goal-oriented discussions. Inspired by this work and by the apparent lack of tooling available to support it, we created Diplomat, a Python-based framework for building conversational agent facilitators. Diplomat is designed to support simple specification of agent functionality as well as customizable integration with online chat services. We document a preliminary user study we conducted to help inform the design of Diplomat. We also describe the architecture, capabilities, and limitations of our tool, which we have shared on GitHub.