Adaptive and implicit interaction techniques in human-computer interaction
Loading...
Date
2025-11-06
Authors
Μαλλάς, Ανδρέας
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
As digital technology becomes ever more embedded in day-to-day activities, control is moving away from deliberate commands toward systems that infer users’ needs. Although such Adaptive User Interfaces (AUI) promise friction-free interaction, unconstrained automation can compromise predictability, transparency, and trust. To mitigate these risks, this dissertation introduces and formalizes Passive Interaction, a deliberately scoped form of implicit adaptation whose purpose is to keep the current experience consistent in an ongoing task as the user’s physical or affective state drifts. Rather than inferring a person’s high-level intentions, a passive system makes unobtrusive adjustments to maintain perceptual stability as a user’s physical or mental state naturally changes.
The dissertation is organized around three interconnected strands. First, it defines Passive Interaction and presents two working prototypes that run on commodity hardware: an adaptive-font web reader for mobile devices that resizes text according to viewing distance and scores highly on usability metrics; and an emotion-aware video game that adjusts game elements to match player affect and is rated on par with commercial titles. Second, it explores eye-tracking as a richer implicit signal. A study with UAV pilots shows how gaze-responsive cockpits could ease cognitive load, while a lecture-slide summarizer personalizes study materials by tracking what learners actually read. Third, a series of foundational studies reveals how objective performance can diverge from subjective preference, how user background and context shape satisfaction, and uncovers robust behavioral patterns, such as block-wise reading, that can inform future adaptive interfaces.
Together, these strands contribute a design framework that reconciles adaptive assistance with predictability; provide empirical evidence that subtle, on-device corrections can be delivered with commodity cameras; and yield actionable insights into how user diversity shapes interface preference, ultimately guiding the design of more effective and trustworthy adaptive systems.
Description
Keywords
Human-computer interaction, Adaptive user interfaces, Implicit interaction, Passive interaction, Context-awareness, Affective computing, Visual attention, Eye-tracking, Usability evaluation, Facial emotion recognition