What do you want to do next

TLDR

Interaction intent prediction and the Midas touch remain longstanding challenges for eye‑tracking researchers and users of gaze‑based interaction. The study develops and tests an offline framework for task‑independent prediction of interaction intents, inspired by machine‑learning approaches in biometric authentication. The framework uses extracted gaze features, normalization techniques, and evaluation metrics, and was systematically tested on a gaze‑augmented problem‑solving dataset. The approach achieved up to 76% accuracy with an AUC of ~80%, and the authors suggest it could support an online interaction‑intent prediction system.

Abstract

Interaction intent prediction and the Midas touch have been a longstanding challenge for eye-tracking researchers and users of gaze-based interaction. Inspired by machine learning approaches in biometric person authentication, we developed and tested an offline framework for task-independent prediction of interaction intents. We describe the principles of the method, the features extracted, normalization methods, and evaluation metrics. We systematically evaluated the proposed approach on an example dataset of gaze-augmented problem-solving sessions. We present results of three normalization methods, different feature sets and fusion of multiple feature types. Our results show that accuracy of up to 76% can be achieved with Area Under Curve around 80%. We discuss the possibility of applying the results for an online system capable of interaction intent prediction.