Litcius/Paper detail

Extending Chatbots to Probe Users: Enhancing Complex Decision-Making Through Probing Conversations

Leon Reicherts, Gun Woo Park, Yvonne Rogers

202225 citationsDOIOpen Access PDF

Abstract

Chatbots have become commonplace – they can provide customer support, take orders, collect feedback, and even provide (mental) health support. Despite this diversity, the opportunities of designing chatbots for more complex decision-making tasks remain largely underexplored. Bearing this in mind leads us to ask: How can chatbots be embedded into software tools used for complex decision-making and designed to scaffold and probe human cognition? The goal of our research was to explore possible uses of such “probing bots”. The domain we examined was stock investment where many complex decisions need to be made. In our study, different types of investors interacted with a prototype, which we called “ProberBot”, and subsequently took part in in-depth interviews. They generally found our ProberBot was effective at supporting their thinking but when this is desirable depends on the type of task and activity. We discuss these and other findings as well as design considerations for developing ProberBots for similar types of decision-making tasks.

Topics & Concepts

Computer scienceTask (project management)Human–computer interactionKnowledge managementCognitionDiversity (politics)PsychologyEngineeringAnthropologyNeuroscienceSociologySystems engineeringAI in Service InteractionsDigital Mental Health InterventionsPersonal Information Management and User Behavior
Extending Chatbots to Probe Users: Enhancing Complex Decision-Making Through Probing Conversations | Litcius