Gaze-based feedback in assessing media relevance

As more and more data contents gathered on the Internet, the problem of data overloading has attracted many research interests. In view of this, it is crucial to understand the user behavior when s/he interacts with online contents. For example, a web page containing several entries for further exploration. Under the assumption that eye movement measures can be used to infer a user’s cognition, we proposed a framework to estimate the relevance of an entry to the user’s goal by recording eye movements as implicit feedback. Fourteen subjects volunteered to perform a rating task in which they were required to judge whether an image was relevant to a word. Results showed that the total fixation duration and the fixation count can be used to discriminate between the relevant and irrelevant conditions; in contrast, the first fixation duration cannot. In addition, the subjective rating and relevancy manipulation interacted on the total fixation duration. Converging evidence verified the assumption in the proposed framework.