Oculomotor Plant
Detailed knowledge about a user’s interests is beneficial in web search, advertising, and personalized information delivery as well as in content targeting. The goal of personalized information delivery is to support users by identifying documents or the parts of a document that best match user’s interests during an open-ended information searching task. Such personalization can result in a more efficient use of the user’s time, e.g. that their time is spent on the most relevant documents. Understanding how the human eye movements and underlying non-visible anatomical structure and its characteristics (oculomotor plant) change over the course of user engagement with information resources will be valuable in the pursuit of developing more accurate user interest models.
This project will provide foundation for an extensive framework expanding the use of eye movements as a source for user interest modeling. This work constructs a model of human oculomotor plant features during user’s interactions with the goal of better interpreting user gaze data related to resource content. The project will explore the anatomical reasoning behind incorporating additional gaze features, the integration of the additional features into an existing interest modeling architecture, and a plan for assessing the impact of the addition of the features.