2022/03/16 by Vidya Setlur, Setlur, Vidya, Melanie Tory +1 · 5 citations
Computer Science · Psychology · #AI in Service Interactions #Affordance #Ambiguity #Artificial intelligence #Chart #Chatbot #Communication #Computer science #Conversation #FOS: Computer and information sciences #H.5 #Human-Computer Interaction (cs.HC) #Human–computer interaction #Psychology #Speech and dialogue systems #Topic Modeling #Variety (cybernetics) #World Wide Web #cs.HC
paper · pdf · doi:10.48550/arxiv.2203.08420
published in arXiv (Cornell University) (Cornell University) · 17 pages, 8 figures
arxiv created 2022/03/16 · openalex publication_date 2022/03/16 · arxiv updated 2022/03/17 · openalex created_date 2022/04/03 · openalex updated_date 2026/08/08
Chatbots have garnered interest as conversational interfaces for a variety of tasks. While general design guidelines exist for chatbot interfaces, little work explores analytical chatbots that support conversing with data. We explore Gricean Maxims to help inform the basic design of effective conversational interaction. We also draw inspiration from natural language interfaces for data exploration to support ambiguity and intent handling. We ran Wizard of Oz studies with 30 participants to evaluate user expectations for text and voice chatbot design variants. Results identified preferences for intent interpretation and revealed variations in user expectations based on the interface affordances. We subsequently conducted an exploratory analysis of three analytical chatbot systems (text + chart, voice + chart, voice-only) that implement these preferred design variants. Empirical evidence from a second 30-participant study informs implications specific to data-driven conversation such as interpreting intent, data orientation, and establishing trust through appropriate system responses.