Enticing notification text & the impact on engagement

Abstract

Push-notifications are a design tool used by mobile and web apps to alert subscribers to new information. In recent years, due to widespread adoption of the technology and the shrinking level of user attention available, marketing techniques have been deployed to persuade subscribers to engage positively with notifications. One such technique, known as the curiosity gap, exploits Lowenstein's Information-Gap theory. This paper explores the impact of enticing notification text, instilled by the curiosity gap, on subsequent engagement actions. A classifier was defined to identify enticing language in notifications. Features commonly paired with enticing text were identified. Intelligent notification delivery agents, trained using data captured in-the-wild, were evaluated using enticing and non-enticing notifications to demonstrate the influence of enticing text. Additionally, a solution was proposed and briefly evaluated for limiting subscriber susceptibility to enticing notifications. CCS CONCEPTS • Human-centered computing → Smartphones; • Computing methodologies → Natural language processing; Reinforcement learning.

Alert Now or Never: Understanding and Predicting Notification Preferences of Smartphone Users

“…Two subjects (user1 and user2) did not want any of their notiications to interrupt them immediately, while three others (user33, user34, and user35) preferred to receive immediate alerts for every notiication. Thirteen of 35 participants (user1, 2,4,11,12,13,15,16,17,18,20,21,26) chose łsend now, alert laterž for some of their notiications, while others did not select this option at all. This suggests that individual diferences afect people's attitudes towards deferring the alert.…”

“…Given that our qualitative analysis has identiied other aspects of user behavior that may correlate with their delivery preferences, such as app usage before or after receiving and dismissing the notiication, we expect incorporating these measures may further improve the prediction accuracy. In addition, as people seemed to use diferent strategies to handle diferent types of notiications, NLP features could be used to automatically identify high-level categories of a notiication [15] and we can feed this information to the model to make more targeted prediction. Due to the small size of our sample, these sophisticated model designs can only be left for future work to evaluate.…”

Now, Later, Never: A Study of Urgency in Mobile Push-Notifications

“…As discussed in Section 2, at the time of writing, no standard feature exists which describe the urgency of a push-notification paired with an assumed period of relevancy. This work proposes a taxonomy to address this gap -APN 7 , first introduced to categorize the call-to-action of notifications [6], classifies urgency through a taxonomy of eight categories. Using such a vocabulary provides the opportunity to improve the transparency and explainability of models developed with the identified urgency labels, beyond the other advantages already mentioned in Section 2.…”

“…Fraser et al [7] studied the impact of this "information-gap" within pushnotifications and emphasized the potential negative impact it could have if consistently used as a dark pattern by marketers for enticing engagement.…”

“…https://www.empushy.com7 Online documentation for APN is available at https://w3id.org/apn/ 8. Crowdsource annotation platform: https://appen.com/…”