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

Justin Edwards, He Liu+5 more|arXiv (Cornell University)|Aug 22, 2019

Personal Information Management and User BehaviorDecision Sciences45 references7 citations

TL;DR

This study investigates how using intelligent personal assistants (IPAs) like Alexa affects language-based primary tasks, finding that content generation tasks—more cognitively demanding and resource-intensive—are significantly disrupted by IPA interactions, while simpler copying tasks are less affected, as explained by cognitive resource theories such as working memory and multiple resource theory.

ABSTRACT

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 for IPA use, are significantly more disrupted by IPA interaction than less demanding tasks such as copying content. We discuss how theories of cognitive resources, including multiple resource theory and working memory, explain these results. We also outline the need for future work how interruption length and relevance may impact primary task performance as well as the need to identify effects of interruption timing in user and IPA led interruptions.

Motivation & Objective

• To examine the impact of IPA use on language-based primary tasks.
• To compare how different cognitive demands of writing tasks (copying vs. content generation) are affected by IPA interactions.
• To explore the role of cognitive resource allocation, particularly working memory and multiple resource theory, in multitasking with IPAs.
• To identify gaps in understanding interruption effects based on timing, length, and relevance.

Proposed method

• Employed a dual-task experimental paradigm to simulate multitasking with IPAs.
• Assigned participants to perform two types of writing tasks: copying text and generating original content.
• Measured performance on primary tasks during and after interactions with an IPA.
• Used cognitive resource theories—specifically working memory and multiple resource theory—as theoretical frameworks to interpret results.
• Collected and analyzed performance metrics such as task completion time and accuracy.
• Controlled for variables like task complexity and interruption timing to isolate IPA impact.

Experimental results

Research questions

• RQ1 How does IPA interaction affect performance on language-based primary tasks with varying cognitive demands?
• RQ2 To what extent do content generation tasks suffer more from IPA interruptions than copying tasks?
• RQ3 How do cognitive resource theories explain the observed differences in task disruption?
• RQ4 How do interruption length and relevance influence primary task performance?
• RQ5 What role does interruption timing—user-initiated vs. IPA-initiated—play in task disruption?

Key findings

• Content generation tasks were significantly more disrupted by IPA interactions than copying tasks due to higher cognitive load.
• Tasks requiring greater working memory and language processing resources showed greater performance degradation during IPA use.
• The findings align with multiple resource theory, indicating that overlapping resource demands impair performance.
• IPA interruptions had a measurable negative impact on task accuracy and completion time, especially in complex writing tasks.
• The study highlights that not all interruptions are equal—cognitive load and task type mediate the extent of disruption.
• Future research is needed to explore how interruption timing and relevance affect task recovery and performance.