SituFont: A Just-in-Time Adaptive Intervention System for Enhancing Mobile Readability in Situational Visual Impairments

TL;DR

SituFont addresses mobile reading under dynamic situational visual impairments by combining context sensing, a label-tree representation, and a human-in-the-loop to adjust font parameters in a just-in-time manner. Grounded in formative studies with $N=15$ interviews and $N=18$ controlled experiments, the design yields population priors that are personalized through user feedback, enabling on-device ML to suggest font size, weight, and spacing. A within-subject user study ($N=12$) shows SituFont improves reading goodput and reduces perceived workload across multiple SVIs while preserving comprehension, with favorable user experience metrics. The work demonstrates practical, privacy-conscious, context-aware typography that can adapt to fast-changing reading environments and paves the way for broader JITAI-based perceptual interventions in mobile UI. The approach offers actionable guidance for deploying adaptive typography in real-world multilingual contexts and informs future cross-script accessibility enhancements.

Abstract

Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobile readability by dynamically adjusting font parameters based on real-time contextual changes. Using smartphone sensors and a human-in-the-loop approach, SituFont personalizes text presentation to accommodate personal factors (e.g., fatigue, distraction) and environmental conditions (e.g., lighting, motion, location). To inform its design, we conducted formative interviews (N=15) to identify key SVI factors and controlled experiments (N=18) to quantify their impact on optimal text parameters. A comparative user study (N=12) across eight simulated SVI scenarios demonstrated SituFont's effectiveness in improving smartphone mobile readability in terms of improved efficiency and reduced workload compared with a non-trivial manual adjustment baseline.

Figures (12)

• Figure 1: Workflow of the Semi-Structured Interviews.
• Figure 2: Interview Findings: Factors Affecting Situational Visual Impairments. The numbers inside the rectangles indicate the proportion of respondents who mentioned each factor.
• Figure 3: Formative study 's findings inspire the system design of SituFont, which mainly include the label tree, machine learning training, human-ai loop modules.
• Figure 4: The user interface of SituFont involves three key interactions: (1) Entering the System – the user confirms or adjusts the detected reading context; (2) Selecting Influence Factors – the user specifies factors affecting readability, such as fatigue or distraction; and (3) Adjusting Text Parameters – the user refines font size, line spacing, thickness, and word spacing through swipe gestures for a personalized reading experience.
• Figure 5: The left part of the figure describes a three-layer labeling system used to mark situations, where the priority decreases from top to bottom when constructing the label tree. The right part of the figure presents an example of a label tree, where the solid lines indicate the process of detecting situational label combinations.