Priming at Scale

An Evaluation of Using AI to Generate Primes for Mobile Readers

Conference Paper (2025)
Author(s)

Namrata Srivastava (Monash University, VanderBilt University)

Jennifer Healey (Adobe Research)

Rajiv Jain (Adobe Research)

Guanli Liu (University of Melbourne)

Ying Ma (University of Melbourne)

Borano Llana (University of Rhode Island)

Dragan Gasevic (Monash University)

Tilman Dingler (TU Delft - Industrial Design Engineering)

Shaun Wallace (University of Rhode Island)

Research Group
Human-Centred Artificial Intelligence
DOI related publication
https://doi.org/10.1145/3706599.3720153 Final published version
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Human-Centred Artificial Intelligence
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Article number
447
Publisher
ACM
ISBN (electronic)
979-8-4007-1395-8
Event
2025 CHI Conference on Human Factors in Computing Systems, CHI 2025 (2025-04-26 - 2025-05-01), Yokohama, Japan
Downloads counter
182
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Text summaries, images, and mind maps are well-known methods for priming readers to better engage with content. Previously, these “primes” needed to be hand-crafted, limiting their use. The advent of generative technologies makes the automatic creation of custom primes for any passage a realistic possibility. Here, we evaluate the efficacy of primes generated using AI on reading comprehension, reading speed, and re-engagement during mobile reading, which is notorious for its frequent interruptions. We used a mobile platform to present a reading task with an interruption to 44 readers (21 with English as a first language). We found that AI primes increased reading speed by an average of 7% for all readers in the initial reading task with no loss of comprehension and that visual primes had a significant interruption recovery effect for people whose first language was not English. Across all readers, text primes had both the initial reading speed increase and were overall most preferred.

Files

3706599.3720153.pdf
(pdf | 15.8 Mb)
- Embargo expired in 25-10-2025
License info not available