The Meant, the Said, and the Understood: Conversational Argument Search and Cognitive Biases

Abstract

Many questions of public interest do not have a single answer but come with a set of choices, each of which with its pros and cons. An "objective" information system can help explore the underlying argument space, and, if equipped with a conversational interface, it can create the experience of lively discussions resembling those from our daily lives. However, users will (subconsciously) extend the provided information by assumptions that adhere to their cognitive biases. In this regard, note that biases do not arise only from the underlying data or the employed algorithms, but also from the way the information is presented-especially in audio-only channels. Our paper brings attention to bias-related challenges of conversational interfaces for argument search systems. We identify research questions that address these challenges, and we propose ideas and methods to tackle them. CCS CONCEPTS• Human-centered computing → Interaction paradigms; • Information systems → Users and interactive retrieval.

Conversational Information Seeking

“…Many open problems related to the support and guiding of searchers through results presentation exist. For example, presentation order bias (Azzopardi, 2021;Kiesel et al, 2021b), interaction with tabular data (Zhang et al, 2020a), personas of the conversational system (Nass and Brave, 2005), persuasiveness of synthetic speech (Dubiel et al, 2020b), meta-communication to support communication breakdowns (Trippas et al, 2018), or using non-speech sounds to increase user engagement with search results (Winters et al, 2019;Arons, 1997). For example, order bias has been suggested to affect which results summaries receive the most attention from users in a visual setting (Joachims et al, Draft Version 1.0 2005).…”