Human Machine Textual Interaction
This paper presents a pilot study involving 99 participants analysing conversations between Judges 2, 4 and 7, hidden humans (Confederates), and Jabberwock, bronze prize winner for most human-like machine from Loebner’s 2003 Contest, instantiation of Turing’s Test for machine intelligence. The transcripts from these conversations were given to children (aged between 8 and 12), and adults (aged between 18-35). The machine was identified in its conversation with Judge 7, but the Confederate Effect featured in the decisions regarding the nature of the Judges and Confederates, who were both sometimes considered machine-like from their textual discourse. Creators of Jabberwock-type systems may find results presented here useful in their human-machine textual interaction designs.
Only registered members are allowed to comment.