Toward Intelligent Meeting Agents

  • Authors:
  • Hsinchun Chen;Andrea Houston;Jay Nunamaker;Jerome Yen

  • Affiliations:
  • -;-;-;-

  • Venue:
  • Computer
  • Year:
  • 1996

Quantified Score

Hi-index 4.10

Visualization

Abstract

An experiment with an AI-based software agent shows that it can help users organize and consolidate ideas from electronic brainstorming. The agent recalled concepts as effectively as experienced human meeting facilitators and in a fifth of the time. Agent software enhances the productivity of groupware by helping perform convergent tasks, thus freeing users for more creative work. The result is a significant time savings over groupware without agents. We validated the performance of an intelligent agent, which can reason about a task and learn from task performance. Our intelligent agent supports the GroupSystems electronic meeting system developed by the University of Arizona. The agent organizes ideas from brainstorming sessions into category lists for further discussion, a task often difficult for human electronic meeting facilitators.