Personalizing a parenting app: parenting-style surveys beat behavioral reading-based models

The present study set out to personalize a digital library aimed at new parents by reordering articles to match users' inferred interests. The interests were inferred from reading behavior as well as parenting styles measured through surveys. As prior research has shown that parenting styles are related to how parents take care of their children, these styles are likely to be related to what content a parent is interested in. The present study compared personalization based on parenting styles against other types of personalization. We conducted a user study with 106 participants, in which we compared the effects of four different approaches of personalization to our users' reading behavior and user experience: a non-personalized baseline, personalization based on reading behavior, personalization based on parenting styles measured through surveys, and a hybrid personalization based on both reading behavior and parenting styles. We found that while the reading behavior was not significantly influenced by different types of personalization, participants had a better user experience with our survey-based approach. They indicated they perceived a higher level of personalization and satisfaction with the system, even though in terms of objective metrics this approach performed worse.

Part of Workshop 4: Theory-Informed User Modeling for Tailoring and Personalizing Interfaces - HUMANIZE