Ziang Xiao 1, Michelle X. Zhou2, Wenxi Chen2, Huahai Yang2, Changyan Chi2

1University of Illinois at Urbana-Champaign, 2Juji, Inc.

Abstract

Interview chatbots engage users in a text-based conversation to draw out their views and opinions. It is, however, chal- lenging to build effective interview chatbots that can handle user free-text responses to open-ended questions and deliver engaging user experience. As the first step, we are investi- gating the feasibility and effectiveness of using publicly available, practical AI technologies to build effective inter- view chatbots. To demonstrate feasibility, we built a proto- type scoped to enable interview chatbots with a subset of ac- tive listening skills—the abilities to comprehend a user’s input and respond properly. To evaluate the effectiveness of our prototype, we compared the performance of interview chatbots with or without active listening skills on four com- mon interview topics in a live evaluation with 206 users. Our work presents practical design implications for building ef- fective interview chatbots, hybrid chatbot platforms, and em- pathetic chatbots beyond interview tasks.