A User-Centered Design Investigation for Conversational Agents for Information Retrieval in Educational Scenarios

Video

DOI

Text-based conversational agents (CAs) are widely deployed across a number of daily tasks, including information retrieval. However, most existing agents follow a default design that disregards user needs and preferences, ultimately leading to a lack of usage and an unsatisfying user experience. More interestingly, deployed CAs are oftentimes not grounded in extant theories. To better understand how CAs can be designed in order to lead to effective system use, we built and tested a question-answering, text-based CA for an information retrieval task in an education scenario. We deduced relevant design requirements from both literature and 13 user interviews. Results from our experimental test with 41 students indicate that following a user-centered design has a significant positive effect on enjoyment with and trust in a CA as opposed to deploying a default CA. Beyond practical implications for effective CA design, this paper points towards key challenges and potential research avenues when deploying social cues for CAs.