Exploring the Role of Interaction Data to Empower End-User Decision-Making In UI Personalization

Abstract

User interface personalization enhances digital efficiency, usability, and accessibility. However, in user-driven setups, limited support for identifying and evaluating worthwhile opportunities often leads to underuse. We explore a reflexive personalization approach where individuals engage with their digital interaction data to identify meaningful personalization opportunities and benefits. We interviewed 12 participants, using experimental vignettes as design probes to support reflection on different forms of using interaction data to empower decision-making in personalization and the preferred level of system support. We found that people can independently identify personalization opportunities but prefer system support through visual personalization suggestions. Interaction data can shape how users perceive and approach personalization by reinforcing the perceived value of change and data collection, helping them weigh benefits against effort, and increasing the transparency of system suggestions. We discuss opportunities for designing personalization software that raises end-users' agency over interfaces through reflective engagement with their interaction data.

Figures (9)

• Figure 1: Two example vignettes illustrating two of the four scenarios in which a hypothetical platform leverages personal interaction data to support the identification and implementation of UI personalization opportunities. Each scenario was illustrated through multiple vignettes, which served as design probes to provoke participant reflection and discussion during the interviews. In these two illustrations, the hypothetical software supports decision-making by generating textual (left) or visual (right) personalization suggestions based on clickstream data. The left vignette shows the original UI overlaid with a click heatmap and textual suggestions (interpretations of the interaction data that highlight potential usability issues and recommend manual personalization actions). The right vignette, through a system-initiated design process, presents visual suggestions, where the system displays a preview of the personalized UI, which users can adopt and further refine, and includes estimated time savings. Similar benefit estimates are also present in other vignette scenarios. Both scenarios illustrate a workflow where users retain personalization control and can personalize their interfaces freely, following a user-driven strategy.
• Figure 2: Structure of the four vignette sets used to support the interviews, where each set represents a different version of UIPulse. Each set consists of a series of vignettes, with their ranges indicated using ellipses (e.g., 15...17). The sequence begins with the presentation of two personas, followed by Set A, which introduces a UIPulse version focused on data visualization dashboards (accessible across all sets). After reflecting on these dashboards, participants are introduced to the concept of personalization through a vignette illustrating a customization tool and invited to consider how interaction data might support personalization. Sets B, C, and D follow a similar structure, each featuring UIPulse illustrations that include both fixed vignettes and vignettes tailored individually for each participant, along with a reflection moment.
• Figure 3: Example vignettes from each of the four UIPulse sets. Each vignette includes a title (combining the vignette name with the title of the analyzed UI) and a brief description.
• Figure 4: Vignette 1: A description of the persona, Alex.
• Figure 5: Vignette A5: Illustration of last week's visits to a specific website.