Proactive behavior in voice assistants: A systematic review and conceptual model

Voice assistants (VAs) are increasingly integrated into everyday activities and tasks, raising novel challenges for users and researchers. One emergent research direction concerns proactive VAs, who can initiate interaction without direct user input, offering unique benefits including efficiency and...

Full description

Saved in:

Bibliographic Details
Published in:	Computers in human behavior reports Vol. 14; p. 100411
Main Authors:	Bérubé, Caterina, Nißen, Marcia, Vinay, Rasita, Geiger, Alexa, Budig, Tobias, Bhandari, Aashish, Pe Benito, Catherine Rachel, Ibarcena, Nathan, Pistolese, Olivia, Li, Pan, Sawad, Abdullah Bin, Fleisch, Elgar, Stettler, Christoph, Hemsley, Bronwyn, Berkovsky, Shlomo, Kowatsch, Tobias, Kocaballi, A. Baki
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01-05-2024 Elsevier
Subjects:	conversational agents Human-agent interaction proactive behavior Proactivity Systematic review User experience Voice assistants voice-based agents conversational agents proactive behavior voice-based agents Proactivity Systematic review User experience Voice assistants Human-agent interaction
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Voice assistants (VAs) are increasingly integrated into everyday activities and tasks, raising novel challenges for users and researchers. One emergent research direction concerns proactive VAs, who can initiate interaction without direct user input, offering unique benefits including efficiency and natural interaction. Yet, there is a lack of review studies synthesizing the current knowledge on how proactive behavior has been implemented in VAs and under what conditions proactivity has been found more or less suitable. To this end, we conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. We searched for articles in the ACM Digital Library, IEEExplore, and PubMed, and included primary research studies reporting user evaluations of proactive VAs, resulting in 21 studies included for analysis. First, to characterize proactive behavior in VAs we developed a novel conceptual model encompassing context, initiation, and action components: Activity/status emerged as the primary contextual element, direct initiation was more common than indirect initiation, and suggestions were the primary action observed. Second, proactive behavior in VAs was predominantly explored in domestic and in-vehicle contexts, with only safety-critical and emergency situations demonstrating clear benefits for proactivity, compared to mixed findings for other scenarios. The paper concludes with a summary of the prevailing knowledge gaps and potential research avenues. •Systematic review of proactive behavior in voice assistants (n = 21 studies).•Novel conceptual model allows to characterize proactive behavior in VAs.•Only safety-critical/emergency situations show clear benefits for proactivity.•Proactive voice assistants still represent a nascent area.•Review identifies research gaps and avenues.
ISSN:	2451-9588 2451-9588
DOI:	10.1016/j.chbr.2024.100411