Multitasking with Alexa: how using intelligent personal assistants impacts language-based primary task performance

@article{Edwards2019MultitaskingWA,
  title={Multitasking with Alexa: how using intelligent personal assistants impacts language-based primary task performance},
  author={Justin Edwards and Herman Chan-En. Liu and Tianyu Zhou and Sandy Gould and Leigh Michael Harry Clark and Philip R. Doyle and Benjamin R. Cowan},
  journal={Proceedings of the 1st International Conference on Conversational User Interfaces},
  year={2019}
}
Intelligent personal assistants (IPAs) are supposed to help us multitask. Yet the impact of IPA use on multitasking is not clearly quantified, particularly in situations where primary tasks are also language based. Using a dual task paradigm, our study observes how IPA interactions impact two different types of writing primary tasks; copying and generating content. We found writing tasks that involve content generation, which are more cognitively demanding and share more of the resources needed… Expand
'Alexa, Do You Know Anything?' The Impact of an Intelligent Assistant on Team Interactions and Creative Performance Under Time Scarcity
Human-AI collaboration is on the rise with the deployment of AI-enabled intelligent assistants (e.g. Amazon Echo, Cortana, Siri, etc.) across organizational contexts. It is claimed that intelligentExpand
See What I’m Saying? Comparing Intelligent Personal Assistant Use for Native and Non-Native Language Speakers
TLDR
The need to tailor the IPA experience for L1 and non-native English speakers interacting with Google Assistant on a smartphone and smart speaker is discussed, emphasising visual feedback whilst reducing the burden of language production. Expand
Eliciting Spoken Interruptions to Inform Proactive Speech Agent Design
TLDR
A new technique was developed to elicit human spoken interruptions of people engaged in other tasks and found that people interrupted sooner when interruptions were urgent, which can inform design of proactive agent interruptions. Expand
Eliciting Spoken Interruptions to Inform Proactive Speech Agent Design
TLDR
A new technique was developed to elicit human spoken interruptions of people engaged in other tasks and found that people interrupted sooner when interruptions were urgent, which can inform design of proactive agent interruptions. Expand
“You, Move There!”: Investigating the Impact of Feedback on Voice Control in Virtual Environments
TLDR
It is found that the type of feedback given by agents is critical to user experience, and specifically auditory mechanisms are preferred, allowing users to engage with other modalities seamlessly during interaction. Expand
Conversational User Interfaces on Mobile Devices: Survey
TLDR
A survey of mobile conversation user interface research since the commercial deployment of Apple's Siri, the first readily available consumer CUI, and the implications for CUIs of greater access to the context of use are presented. Expand
CUI @ Auto-UI: Exploring the Fortunate and Unfortunate Futures of Conversational Automotive User Interfaces
This work aims to connect the Automotive User Interfaces (Auto-UI) and Conversational User Interfaces (CUI) communities through discussion of their shared view of the future of automotiveExpand
Using structural topic modelling to predict users’ sentiment towards intelligent personal agents. An application for Amazon’s echo and Google Home
Abstract Despite growing levels of usage of Intelligent Personal Assistants (hereinafter, IPA), their in-home usage has not been studied in depth by scholars. To increase our understanding of userExpand
Building and Designing Expressive Speech Synthesis
TLDR
A test for computer voices—the Ebert test, where a computer voice can successfully tell a joke and do the timing and delivery as well as Henny Youngman, then that’s the voice I want. Expand

References

SHOWING 1-10 OF 55 REFERENCES
A Survey Investigating Usage of Virtual Personal Assistants
TLDR
The results indicate that, compared with infrequent users, frequent users of VPAs are more satisfied with their assistants, more eager to use them in a variety of settings, yet equally concerned about their privacy. Expand
Cars, calls, and cognition: investigating driving and divided attention
TLDR
A controlled study involving 18 users using a driving simulator showed significant interactions between the primary and secondary tasks, where certain combinations of complexity and conversations were found especially detrimental to driving. Expand
The problem state: a cognitive bottleneck in multitasking.
TLDR
Computational cognitive models were developed using threaded cognition within the context of the cognitive architecture ACT-R and confirm that a problem state bottleneck can explain the observed interference. Expand
What does it mean for an interruption to be relevant? An investigation of relevance as a memory effect
TLDR
The results suggest that interruption relevance is contingent on the contents of working memory during an interruption and that interruption management systems could be improved by modelling potential interfering and reinforcing effects of incoming interruptions. Expand
Talking with Conversational Agents in Collaborative Action
TLDR
This one-day workshop intends to bring together both academics and industry practitioners to explore collaborative challenges in speech interaction to begin a dialogue that takes on the renewed interest in research on spoken interaction with devices, grounded in the existing practices of the CSCW community. Expand
Strategic Adaptation to Performance Objectives in a Dual-Task Setting
TLDR
A study in which participants manually dialed a UK-style telephone number while driving a simulated vehicle shows that drivers choose to return attention to steering control before the natural subtask boundary, supporting the idea that people can strategically control the allocation of attention in multitask settings to meet specific performance criteria. Expand
Instant Messaging and Interruption: Influence of Task Type on Performance
TLDR
It is shown that notifications are more disruptive for fast, stimulus-driven search tasks than for slower, more effortful semantic-based search tasks and alternative hypotheses about the nature of disruption for a list evaluation task are investigated. Expand
"Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents
TLDR
This paper reports the findings of interviews with 14 users of CAs in an effort to understand the current interactional factors affecting everyday use, and finds user expectations dramatically out of step with the operation of the systems. Expand
Not Now! Supporting Interruption Management by Indicating the Modality and Urgency of Pending Tasks
TLDR
The results show that advance knowledge about the nature of pending tasks led participants to delay visual interruption tasks the longest, which allowed them to avoid intramodal interference and scanning costs associated with performing these tasks concurrently with ATC tasks. Expand
"What can i help you with?": infrequent users' experiences of intelligent personal assistants
TLDR
Key challenges are discussed, including: designing for interruptability; reconsideration of the human metaphor; issues of trust and data ownership; and addressing these challenges may lead to more widespread IPA use. Expand
...
1
2
3
4
5
...