Detail:The purpose of this research was to advance the understanding of the behavior of small groups in online chat rooms. The research was conducted using Internet chat data collected through planned exercises with recruited participants, under an approved IRB protocol. Analysis of the collected data led to construction of preliminary models of social behavior in online discourse. Some of these models, e.g., how to effectively change the topic of conversation, were subsequently implemented into an automated Virtual Chat Agent (VCA) prototype. VCA has been demonstrated to perform effectively and convincingly in Internet conversation with human participants. Additional software developed include adaptation of COLLANE-Timeline Tools (IC-TILT) and information extraction tools (LMC AeroText) for analyzing the dialogue, topic tracking, and generating appropriate utterances. VCA technology represents a major advance in automated human-computer communication with potential applications in cross-cultural social modeling, influence operations, advertising, law enforcement, and national security.

Publications from this project

C2, C4