Eye-tracking based adaptive user interface: implicit human-computer interaction for preference indication

In this paper, we proposed and evaluated an adaptive recommendation system based on users' eye-tracking data and an optimization algorithm called IGA. An eye tracker was utilized to acquire users' eye movement data and extract three measures, which were respectively number of fixation, fixation duration and the first fixation on target item. Based on the results on the three measures, we inferred users' preferences and adjusted the user interfaces based on users' preferences. We developed a prototype system, which could adaptively recommend digital cameras to users. Then we conducted a user study with the prototype system and found that participants could identify their preferred products with a comparatively less time period and higher satisfaction.