Smitha Sheshadri, Linus Cheng, and Kotaro Hara

CHI EA '22: CHI Conference on Human Factors in Computing Systems Extended Abstracts, April 2022, Article No.: 221, Pages 1–6, https://doi.org/10.1145/3491101.3519617

We propose a model to achieve human localization in indoor environments through intelligent conversation between users and an agent. We investigated the feasibility of conversational localization by conducting two studies. First, we conducted a Wizard-of-Oz study with N = 7 participants and studied the feasibility of localizing users through conversation. We identified challenges posed by users’ language and behavior. Second, we collected N = 800 user descriptions of virtual indoor locations from N = 80 Amazon Mechanical Turk participants to analyze user language. We explored the effects of conversational agent behavior and observed that people describe indoor locations differently based on how the agent presents itself. We devise “Entity Suitability Scale,” a concrete and scalable approach to obtain information to support localization from the myriad of indoor entities users mention in their descriptions. Through this study, we lay foundation to our proposed paradigm of conversational localization.