Intentions, Meanings, and Whys: Designing Content for Voice-based Conversational Museum Guides

If an artwork could talk, what would visitors ask? This paper explores what types of content voice-based AI conversational systems should have to attend visitors' expectations in a museum. The study analyses 142,463 conversation logs from 5,242 unique sessions of a nine-month long deployment of a voice-based interactive guide in a modern art museum in Brazil. In this experiment, visitors freely asked questions about seven different artworks of different styles. By grouping the visitor utterances into eight types of content, we determined that more than half of the visitors asked about the meanings and intentions behind the artwork, followed by facts about the artwork and author-related questions. We also determined that the types of questions were not affected by each artwork, the artwork style, or its physical location. We also saw some relationships between the visitor's overall evaluation of the experience with the types of questions she asked. Based on those results, we identified implications for designing content for voice-based conversational systems in museums.