Evaluation of the content of computer-aided conversations

Abstract

The study reports an experimental evaluation of the content of computer-aided and unaided conversations on the same fairly broad topic (i.e., holidays). The computer-aided conversations involved volunteers and one of the researchers, who simulated a nonspeaking person using an alternative communication system, “TALK” (talk aid using preloaded knowledge). The unaided conversations were between pairs of volunteers. Transcripts of randomly sampled sections of the conversations and audio recordings of re-enactments of the samples with pauses removed were rated for social competence on a six-item scale (coefficient alpha = 0.83) by 24 judges. The content of the TALK-aided samples was rated significantly higher than that of the unaided samples (p < .001). The judges also rated the individual contributions of the TALK user and her unaided partners on how “socially worthwhile and involving” these appeared. There was no significant difference between the ratings of their respective contributions (p > .05).

• aided and unaided communication
• assistive devices
• communication efficacy
• computers
• content evaluation
• conversation
• dialogue evaluation
• pragmatic intervention
• prestored text
• social competence
• speech output
• VOCA