“…Paired/group discussion tasks, in which two or more test-takers discuss an assigned topic without substantial involvement of an examiner (Philp et al, 2014), are shown to be effective in assessing aspects of second language (L2) oral communication ability (OCA; e.g., Bonk & Ockey, 2003; Leaper & Brawn, 2019; Taylor, 2011), especially interactional competence (IC; e.g., Galaczi, 2014; Lam, 2018; May et al, 2020). However, the use of these tasks in large-scale assessments remains limited due to the impracticality of task administration and the potential impact of interlocutor characteristics, such as personality (e.g., Ockey, 2009), acquaintanceship (e.g., O’Sullivan, 2002), and proficiency level (e.g., Artunc & Hart, 2020), on performance. With recent technological advances, these issues can be addressed by building spoken dialog systems (SDSs), computer programs designed to interact with humans in natural spoken language, to deliver versions of paired/group discussion tasks where computers serve as conversation partners (i.e., interlocutors).…”