“Alexa, Do You Want to Build a Snowman?” Characterizing Playful Requests to Conversational Agents

Conversational Agents (CAs) such as Apple’s Siri and Amazon’s Alexa are well-suited for task-oriented interactions (“Call Jason”), but other interaction types are often beyond their capabilities. One notable example is playful requests: for example, people ask their CAs personal questions (“What’s your favorite color?”) or joke with them, sometimes at their expense (“Find Nemo”). Failing to recognize playfulness causes user dissatisfaction and abandonment, destroying the precious rapport with the CA. Today, playful CA behavior is achieved through manually curated replies to hard-coded questions. We take a step towards understanding and scaling playfulness by characterizing playful opportunities. To map the problem’s landscape, we draw inspiration from humor theories and analyze real user data. We present a taxonomy of playful requests and explore its prevalence in real Alexa traffic. We hope to inspire new avenues towards more human-like CAs.